aiskillstore/marketplace / skills/1102tools-dev/igce-builder-lh-tm
igce-builder-lh-tm
VerifiedTrigger for: Labor-Hour IGCE, LH estimate, Time-and-Materials IGCE, T&M estimate, burdened hourly rate, burden multiplier, labor-category ceiling hours, materials estimate, proposed LH/T&M rate validation, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable LH/T&M estimates using BLS OEWS wages, explicit burden multipliers, GSA CALC+ positioning, GSA Per Diem travel, and separately priced T&M materials. Do NOT use for FFP, cost-reimbursement, grants, or cooperative agreements. Requires the bls-oews, gsa-calc, and gsa-perdiem MCP servers.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.7 KB |
| agents/openai.yaml | config | 297 B |
| references/data-source-operations.md | markdown | 13.4 KB |
| references/runtime-adaptation.md | markdown | 2.7 KB |
| references/validation-gates.md | markdown | 3.9 KB |
| references/workbook-specification.md | markdown | 5.9 KB |
| references/wrap-rate-presets.md | markdown | 2.8 KB |
| scripts/recompute_expected_values.py | script | 8.4 KB |
| scripts/validate_workbook.py | script | 22.3 KB |
| skill-report.json | config | 51.5 KB |
| test.md | markdown | 3.8 KB |
| testing.md | markdown | 31.6 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-08-24T12:50:22.939Z",
"slug": "1102tools-dev-igce-builder-lh-tm",
"source_url": "https://github.com/1102tools-dev/federal-contracting-skills/tree/6c8edf1c45e63acd1bdbb276392924435dde28b3/skills/igce-builder-lh-tm",
"source_ref": "6c8edf1c45e63acd1bdbb276392924435dde28b3",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "ab7a444eb8def5cb8456ff529b6e561f0ae779abe3fa0de6b347a8a589aeb799",
"tree_hash": "0bb1c3c055200cd3d0ebc8e828ab68bdfff72d19af396e4decbf2543887e96c0",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
},
"upstream_version_raw": null,
"upstream_version_normalized": null,
"upstream_version_source": "none",
"upstream_version_status": "missing",
"upstream_commit_sha": "6c8edf1c45e63acd1bdbb276392924435dde28b3"
},
"skill": {
"name": "igce-builder-lh-tm",
"description": "Build auditable Labor-Hour and Time-and-Materials Independent Government Cost Estimates with BLS wages, burden scenarios, CALC+ benchmarks, travel, materials, and workbook validation.",
"summary": "Create validated LH and T&M cost-estimate workbooks with transparent assumptions and source records.",
"icon": "📦",
"author": "1102tools-dev",
"license": "MIT",
"category": "office",
"tags": [
"federal-contracting",
"cost-estimation",
"igce",
"spreadsheets",
"labor-rates"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"filesystem"
]
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "All 59 static findings are false positives. The only executable process call invokes a discovered LibreOffice binary with a fixed argument list and no shell, while other matches are temporary-file handling, Markdown formatting, test prose, or ordinary estimation terminology.",
"remediation": [],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "scripts/validate_workbook.py",
"line_start": 382,
"line_end": 382
},
{
"file": "SKILL.md",
"line_start": 35,
"line_end": 35
},
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 43,
"line_end": 43
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 49
},
{
"file": "SKILL.md",
"line_start": 69,
"line_end": 69
},
{
"file": "SKILL.md",
"line_start": 96,
"line_end": 96
},
{
"file": "SKILL.md",
"line_start": 118,
"line_end": 118
},
{
"file": "SKILL.md",
"line_start": 122,
"line_end": 122
},
{
"file": "SKILL.md",
"line_start": 146,
"line_end": 149
},
{
"file": "SKILL.md",
"line_start": 149,
"line_end": 159
},
{
"file": "SKILL.md",
"line_start": 159,
"line_end": 166
},
{
"file": "SKILL.md",
"line_start": 166,
"line_end": 171
},
{
"file": "SKILL.md",
"line_start": 171,
"line_end": 177
},
{
"file": "SKILL.md",
"line_start": 177,
"line_end": 177
},
{
"file": "SKILL.md",
"line_start": 210,
"line_end": 213
},
{
"file": "testing.md",
"line_start": 184,
"line_end": 184
}
]
},
{
"factor": "filesystem",
"evidence": [
{
"file": "scripts/validate_workbook.py",
"line_start": 13,
"line_end": 13
},
{
"file": "scripts/validate_workbook.py",
"line_start": 364,
"line_end": 364
},
{
"file": "scripts/validate_workbook.py",
"line_start": 365,
"line_end": 365
},
{
"file": "scripts/validate_workbook.py",
"line_start": 491,
"line_end": 491
},
{
"file": "scripts/validate_workbook.py",
"line_start": 372,
"line_end": 372
}
]
}
],
"static_findings": [
{
"id": "sensitive:references/data-source-operations.md:165:certificate-key-files",
"category": "sensitive",
"severity": "high",
"pattern": "Certificate/key files",
"file": "references/data-source-operations.md",
"line_start": 165,
"line_end": 165,
"snippet": "aggregations.labor_category.buckets[*].key"
},
{
"id": "blocker:references/data-source-operations.md:29:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/data-source-operations.md",
"line_start": 29,
"line_end": 29,
"snippet": "Serialize credentialed federal API calls and leave at least three seconds between them, including ca"
},
{
"id": "blocker:references/data-source-operations.md:114:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/data-source-operations.md",
"line_start": 114,
"line_end": 114,
"snippet": "The requested datatypes provide mean plus P10, P25, P50, P75, and P90. Valid operation datatypes inc"
},
{
"id": "blocker:references/data-source-operations.md:133:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/data-source-operations.md",
"line_start": 133,
"line_end": 133,
"snippet": "- Mid or journeyman: P50"
},
{
"id": "blocker:references/workbook-specification.md:23:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/workbook-specification.md",
"line_start": 23,
"line_end": 23,
"snippet": "| A3 / B3 | Mid Burden Multiplier / input |"
},
{
"id": "blocker:references/workbook-specification.md:57:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/workbook-specification.md",
"line_start": 57,
"line_end": 57,
"snippet": "- Mid IGCE total"
},
{
"id": "blocker:references/workbook-specification.md:59:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/workbook-specification.md",
"line_start": 59,
"line_end": 59,
"snippet": "- Difference between the mid IGCE and ceiling input"
},
{
"id": "blocker:references/workbook-specification.md:81:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/workbook-specification.md",
"line_start": 81,
"line_end": 81,
"snippet": "| 8 | Mid Multiplier | `='IGCE Summary'!$B$3` |"
},
{
"id": "blocker:references/workbook-specification.md:82:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/workbook-specification.md",
"line_start": 82,
"line_end": 82,
"snippet": "| 9 | Mid Burdened Rate | direct rate times mid multiplier |"
},
{
"id": "blocker:references/wrap-rate-presets.md:7:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/wrap-rate-presets.md",
"line_start": 7,
"line_end": 7,
"snippet": "| Environment | Low | Mid | High | Use |"
},
{
"id": "blocker:scripts/recompute_expected_values.py:181:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/recompute_expected_values.py",
"line_start": 181,
"line_end": 181,
"snippet": "raise InputError(f\"invalid JSON in {path}: {exc}\") from exc"
},
{
"id": "external_commands:scripts/validate_workbook.py:382:python-subprocess-run",
"category": "external_commands",
"severity": "high",
"pattern": "Python subprocess.run",
"file": "scripts/validate_workbook.py",
"line_start": 382,
"line_end": 382,
"snippet": "completed = subprocess.run(command, capture_output=True, text=True, timeout=120, check=False)"
},
{
"id": "filesystem:scripts/validate_workbook.py:13:temp-file-creation",
"category": "filesystem",
"severity": "low",
"pattern": "Temp file creation",
"file": "scripts/validate_workbook.py",
"line_start": 13,
"line_end": 13,
"snippet": "import tempfile"
},
{
"id": "filesystem:scripts/validate_workbook.py:364:temp-file-creation",
"category": "filesystem",
"severity": "low",
"pattern": "Temp file creation",
"file": "scripts/validate_workbook.py",
"line_start": 364,
"line_end": 364,
"snippet": "def recalculate_with_libreoffice(source: Path, executable: Path) -> tuple[tempfile.TemporaryDirector"
},
{
"id": "filesystem:scripts/validate_workbook.py:365:temp-file-creation",
"category": "filesystem",
"severity": "low",
"pattern": "Temp file creation",
"file": "scripts/validate_workbook.py",
"line_start": 365,
"line_end": 365,
"snippet": "temp = tempfile.TemporaryDirectory(prefix=\"lh-tm-workbook-validation-\")"
},
{
"id": "filesystem:scripts/validate_workbook.py:491:temp-file-creation",
"category": "filesystem",
"severity": "low",
"pattern": "Temp file creation",
"file": "scripts/validate_workbook.py",
"line_start": 491,
"line_end": 491,
"snippet": "temp: tempfile.TemporaryDirectory[str] | None = None"
},
{
"id": "filesystem:scripts/validate_workbook.py:372:python-shutil-operations",
"category": "filesystem",
"severity": "medium",
"pattern": "Python shutil operations",
"file": "scripts/validate_workbook.py",
"line_start": 372,
"line_end": 372,
"snippet": "shutil.copy2(source, copied)"
},
{
"id": "blocker:scripts/validate_workbook.py:48:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/validate_workbook.py",
"line_start": 48,
"line_end": 48,
"snippet": "raise InputError(f\"invalid workbook cell reference: {reference}\")"
},
{
"id": "blocker:scripts/validate_workbook.py:419:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/validate_workbook.py",
"line_start": 419,
"line_end": 419,
"snippet": "(\"workbook_mid_rate_cell\", \"burdened_mid_rate\", \"mid rate\"),"
},
{
"id": "blocker:scripts/validate_workbook.py:421:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/validate_workbook.py",
"line_start": 421,
"line_end": 421,
"snippet": "(\"workbook_mid_total_cell\", \"labor_mid_total\", \"mid labor total\"),"
},
{
"id": "blocker:scripts/validate_workbook.py:435:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/validate_workbook.py",
"line_start": 435,
"line_end": 435,
"snippet": "(\"workbook_mid_total_cell\", \"mid_estimated_total\", \"mid estimated total\"),"
},
{
"id": "blocker:scripts/validate_workbook.py:540:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/validate_workbook.py",
"line_start": 540,
"line_end": 540,
"snippet": "print(f\"Independent mid estimated total: {expected['mid_estimated_total']:.2f}\")"
},
{
"id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 35,
"line_end": 35,
"snippet": "- Use neutral positional language such as `at CALC+ P77 (n=42)` or `above P50 by 18%`."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 38,
"line_end": 38,
"snippet": "- Preserve user-supplied rationale and conclusions verbatim and label any resulting document `DRAFT`"
},
{
"id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 43,
"line_end": 43,
"snippet": "2. **CALC+ signature:** Use `/v3/api/ceilingrates/` with `keyword=`. Never use `q=`; it silently ret"
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 49,
"line_end": 49,
"snippet": "8. **Aging formula:** Store BLS vintage and contract start as `YYYY-MM`. Calculate month gap with `V"
},
{
"id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 69,
"line_end": 69,
"snippet": "Use for raw requirements or the approved staffing handoff from `sow-pws-builder`. For raw requiremen"
},
{
"id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 96,
"line_end": 96,
"snippet": "4. Before workbook creation, require `.xlsx` authoring, Python 3.10+, openpyxl, and the bundled vali"
},
{
"id": "external_commands:SKILL.md:118:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 118,
"line_end": 118,
"snippet": "User-supplied productive hours control. If total hours and FTE are supplied without productive hours"
},
{
"id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 122,
"line_end": 122,
"snippet": "Treat a user-reviewed `STAFFING HANDOFF TABLE` as approved input regardless of heading punctuation."
},
{
"id": "external_commands:SKILL.md:146:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 146,
"line_end": 149,
"snippet": "```text"
},
{
"id": "external_commands:SKILL.md:149:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 149,
"line_end": 159,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:159:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 159,
"line_end": 166,
"snippet": "1. Call `detect_latest_year` and record the runtime vintage."
},
{
"id": "external_commands:SKILL.md:166:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 166,
"line_end": 171,
"snippet": "```text"
},
{
"id": "external_commands:SKILL.md:171:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 171,
"line_end": 177,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:177:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 177,
"line_end": 177,
"snippet": "Use `igce_benchmark` for compact statistics. Use `keyword_search` only when category buckets are nee"
},
{
"id": "external_commands:SKILL.md:210:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 210,
"line_end": 213,
"snippet": "2. Run `scripts/validate_workbook.py <workbook> --expected <sidecar> --engine auto`."
},
{
"id": "blocker:SKILL.md:53:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 53,
"line_end": 53,
"snippet": "12. **Credentialed API pacing:** Serialize credentialed federal API calls and leave at least three s"
},
{
"id": "blocker:test.md:34:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "test.md",
"line_start": 34,
"line_end": 34,
"snippet": "- Valid numeric-zero handling fixture: pass through the integrated validator."
},
{
"id": "blocker:test.md:46:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "test.md",
"line_start": 46,
"line_end": 46,
"snippet": "- Independent mid estimate: matched within validator tolerance"
},
{
"id": "blocker:test.md:43:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "test.md",
"line_start": 43,
"line_end": 44,
"snippet": "- Formula-structure audit: pass"
},
{
"id": "blocker:test.md:44:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "test.md",
"line_start": 44,
"line_end": 45,
"snippet": "- Independent low, mid, and high recomputation: pass"
},
{
"id": "blocker:test.md:45:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "test.md",
"line_start": 45,
"line_end": 46,
"snippet": "- LibreOffice formula execution and cached-value comparison: pass"
},
{
"id": "blocker:test.md:56:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "test.md",
"line_start": 56,
"line_end": 57,
"snippet": "- Skill frontmatter validator: pass"
},
{
"id": "blocker:test.md:58:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "test.md",
"line_start": 58,
"line_end": 59,
"snippet": "- Python compile and command-line help: pass"
},
{
"id": "external_commands:testing.md:184:process-fork",
"category": "external_commands",
"severity": "high",
"pattern": "Process fork",
"file": "testing.md",
"line_start": 184,
"line_end": 184,
"snippet": "3. **Step 9 `present_files` CLI mismatch.** CLI does not have `present_files`. Worker improvised a f"
},
{
"id": "blocker:testing.md:7:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 7,
"line_end": 7,
"snippet": "Independent testing in April 2026 (3 end-to-end runs, 42 binary assertions graded, Claude Opus 4.7) "
},
{
"id": "blocker:testing.md:16:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 16,
"line_end": 16,
"snippet": "| S2: T&M hybrid with $250K/yr materials at NAVWAR San Diego (4 LCATs, base + 2 options) | 12/14 | M"
},
{
"id": "blocker:testing.md:25:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 25,
"line_end": 25,
"snippet": "**1. Skill announced itself.** First line of the worker's response should acknowledge \"IGCE Builder "
},
{
"id": "blocker:testing.md:95:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 95,
"line_end": 95,
"snippet": "2. **Assumption block cell-reference drift (Step 8).** Skill prose at line 465 did not explicitly ma"
},
{
"id": "blocker:testing.md:97:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 97,
"line_end": 97,
"snippet": "3. **Post-recalc per-FTE sanity gate missing.** `recalc.py` returning zero formula errors is necessa"
},
{
"id": "blocker:testing.md:176:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 176,
"line_end": 176,
"snippet": "Workbook built cleanly, $12.5M mid 3-year total, all 3 sanity gates passed (per-FTE in [100K,1M], Sh"
},
{
"id": "blocker:testing.md:195:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 195,
"line_end": 195,
"snippet": "Workbook built cleanly, $9.7M mid 3-year total. PM divergence-triggered re-pick caught +53.7% overpr"
},
{
"id": "blocker:testing.md:272:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 272,
"line_end": 272,
"snippet": "- Grader did not coach workers during runs"
},
{
"id": "blocker:testing.md:321:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 321,
"line_end": 321,
"snippet": "| 3 | USCIS ELIS modernization, raw SOW Workflow A+ | Both patches correctly abstained; Stage A/B ga"
},
{
"id": "blocker:testing.md:328:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 328,
"line_end": 328,
"snippet": "- **Block layout** said `+7: Burdened Mid` (row 7 for block 1 under the natural \"+N = N-th row of bl"
},
{
"id": "blocker:testing.md:329:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 329,
"line_end": 329,
"snippet": "- **Gate 3** said `row +9 = Burdened Mid at B9`."
},
{
"id": "blocker:testing.md:331:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 331,
"line_end": 331,
"snippet": "Under either possible interpretation of \"+N\", Gate 3 was reading the wrong cell: B9 is either a blan"
},
{
"id": "blocker:testing.md:336:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "testing.md",
"line_start": 336,
"line_end": 336,
"snippet": "3. Per-block formula added: for block N, the Burdened Mid cell is `B{7 + (N-1)*15}`."
}
],
"finding_verdicts": [
{
"id": "sensitive:references/data-source-operations.md:165:certificate-key-files",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The word key is a documented CALC+ response-field name inside a data path, not a certificate, private key, or sensitive file."
},
{
"id": "blocker:references/data-source-operations.md:29:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line instructs clients to pace authorized federal API calls and respect rate limits; it does not perform reconnaissance."
},
{
"id": "blocker:references/data-source-operations.md:114:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is documentation for valid BLS statistical datatype identifiers, with no system inspection or discovery behavior."
},
{
"id": "blocker:references/data-source-operations.md:133:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The term Mid describes a labor seniority level mapped to the BLS median, not host or network reconnaissance."
},
{
"id": "blocker:references/workbook-specification.md:23:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This row defines a workbook input cell for a mid burden multiplier and contains no reconnaissance operation."
},
{
"id": "blocker:references/workbook-specification.md:57:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This bullet names the mid-scenario IGCE total required in a workbook, not a system-discovery action."
},
{
"id": "blocker:references/workbook-specification.md:59:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This bullet specifies a cost comparison between estimate and ceiling cells and has no reconnaissance behavior."
},
{
"id": "blocker:references/workbook-specification.md:81:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is an Excel cell-reference formula for the mid multiplier, not system inspection."
},
{
"id": "blocker:references/workbook-specification.md:82:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This table row defines the mid burdened-rate calculation and contains no host or network discovery."
},
{
"id": "blocker:references/wrap-rate-presets.md:7:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Low, Mid, and High are cost-estimate scenario columns in a reference table, not reconnaissance commands."
},
{
"id": "blocker:scripts/recompute_expected_values.py:181:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The code reports a JSON parsing error for a caller-supplied path and does not enumerate or inspect system resources."
},
{
"id": "external_commands:scripts/validate_workbook.py:382:python-subprocess-run",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The validator invokes a discovered LibreOffice executable with a fixed argument list, shell execution disabled by default, and a timeout; no command string or user-controlled option injection is present."
},
{
"id": "filesystem:scripts/validate_workbook.py:13:temp-file-creation",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line only imports Python's tempfile module for isolated workbook recalculation."
},
{
"id": "filesystem:scripts/validate_workbook.py:364:temp-file-creation",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This function creates and returns a managed temporary directory for LibreOffice output, which is legitimate validator behavior."
},
{
"id": "filesystem:scripts/validate_workbook.py:365:temp-file-creation",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "TemporaryDirectory creates an isolated location with a fixed prefix and supports automatic cleanup."
},
{
"id": "filesystem:scripts/validate_workbook.py:491:temp-file-creation",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is only a type-annotated variable used to retain the temporary directory until validation completes."
},
{
"id": "filesystem:scripts/validate_workbook.py:372:python-shutil-operations",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The validator copies the selected workbook into its newly created temporary input directory before recalculation; it does not overwrite the source."
},
{
"id": "blocker:scripts/validate_workbook.py:48:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line rejects malformed workbook cell references and performs no system reconnaissance."
},
{
"id": "blocker:scripts/validate_workbook.py:419:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The tuple maps expected workbook and calculated mid-rate fields for validation, not system discovery."
},
{
"id": "blocker:scripts/validate_workbook.py:421:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The tuple names mid-total workbook fields used in arithmetic comparison and contains no reconnaissance logic."
},
{
"id": "blocker:scripts/validate_workbook.py:435:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This tuple identifies estimate fields for workbook validation, not host or network inspection."
},
{
"id": "blocker:scripts/validate_workbook.py:540:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The script prints an independently calculated mid estimate to the user and reveals no system information."
},
{
"id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks are Markdown code formatting around sample CALC+ positioning language, not shell execution."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks format the document label DRAFT in prose and do not invoke a command."
},
{
"id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks format API path and query-parameter names in documentation, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks identify spreadsheet functions and a date format in Markdown prose; they are not command substitutions."
},
{
"id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks format the name of another skill referenced as an input source."
},
{
"id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks format the xlsx extension in a prerequisite list and do not execute anything."
},
{
"id": "external_commands:SKILL.md:118:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks format an arithmetic expression explaining productive-hours calculation."
},
{
"id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks format the title of a staffing handoff table in documentation."
},
{
"id": "external_commands:SKILL.md:146:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "This line opens a fenced text block containing a staffing arithmetic formula, not an executable block."
},
{
"id": "external_commands:SKILL.md:149:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "This line closes a Markdown text fence and cannot execute a command."
},
{
"id": "external_commands:SKILL.md:159:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks format an MCP operation name that the host resolves through its tool interface."
},
{
"id": "external_commands:SKILL.md:166:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "This line opens a fenced text block of labor-rate equations and is not executable shell content."
},
{
"id": "external_commands:SKILL.md:171:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "This line closes a Markdown text fence and performs no process execution."
},
{
"id": "external_commands:SKILL.md:177:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 1,
"reason": "The backticks format MCP operation names used for CALC+ data retrieval, not shell commands."
},
{
"id": "external_commands:SKILL.md:210:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a documented local validator command with explicit workbook and sidecar arguments, not Ruby backtick execution."
},
{
"id": "blocker:SKILL.md:53:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line imposes conservative pacing and retry limits on authorized API calls and does not instruct reconnaissance."
},
{
"id": "blocker:test.md:34:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a regression-test result for numeric-zero workbook handling, not a reconnaissance instruction."
},
{
"id": "blocker:test.md:46:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line reports a workbook estimate comparison within tolerance and does not inspect system resources."
},
{
"id": "blocker:test.md:43:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line records that a spreadsheet formula-structure audit passed; no network action is described."
},
{
"id": "blocker:test.md:44:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line reports independent cost recomputation results and contains no network discovery."
},
{
"id": "blocker:test.md:45:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This test result concerns local LibreOffice formula execution and cached values, not network reconnaissance."
},
{
"id": "blocker:test.md:56:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line reports a frontmatter validation result and performs no network operation."
},
{
"id": "blocker:test.md:58:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line reports Python compilation and command-line help checks, with no network scanning or discovery."
},
{
"id": "external_commands:testing.md:184:process-fork",
"verdict": "false_positive",
"confidence": 1,
"reason": "The phrase environment fork describes alternate artifact-delivery paths in test documentation; it is not a process fork."
},
{
"id": "blocker:testing.md:7:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line summarizes independent test coverage and model results, not system reconnaissance."
},
{
"id": "blocker:testing.md:16:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line describes a T&M test scenario and its assertion score without inspecting a system."
},
{
"id": "blocker:testing.md:25:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a test expectation for the first line of a response, not a reconnaissance directive."
},
{
"id": "blocker:testing.md:95:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line documents a prior workbook cell-reference defect and contains no host discovery behavior."
},
{
"id": "blocker:testing.md:97:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line discusses a missing workbook sanity check and not reconnaissance."
},
{
"id": "blocker:testing.md:176:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line reports workbook totals and validation gates from a test run, with no system inspection."
},
{
"id": "blocker:testing.md:195:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line summarizes a test estimate and benchmark adjustment, not system reconnaissance."
},
{
"id": "blocker:testing.md:272:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This testing-method statement says graders did not coach workers and contains no reconnaissance action."
},
{
"id": "blocker:testing.md:321:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line records a workflow test result for a raw SOW scenario and does not inspect system resources."
},
{
"id": "blocker:testing.md:328:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line explains a spreadsheet row-offset convention and has no reconnaissance intent."
},
{
"id": "blocker:testing.md:329:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line cites a workbook cell used by a validation gate, not system discovery."
},
{
"id": "blocker:testing.md:331:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line analyzes a wrong spreadsheet-cell comparison and contains no host or network inspection."
},
{
"id": "blocker:testing.md:336:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a corrected spreadsheet formula for locating each block's mid-rate cell, not reconnaissance."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 11,
"total_lines": 2089,
"audit_model": "codex",
"audited_at": "2026-08-24T12:50:22.939Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Build Auditable Labor-Hour and T&M IGCEs",
"value_statement": "Federal buyers need transparent LH and T&M estimates that separate labor, travel, materials, and ceilings. This skill builds validated workbooks from documented assumptions and government benchmarks.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"Labor-Hour IGCE",
"Time-and-Materials IGCE",
"federal cost estimate",
"BLS OEWS wages",
"GSA CALC+ rates",
"T&M workbook"
],
"actual_capabilities": [
"Maps approved labor categories to SOC codes and BLS wage percentiles.",
"Builds low, mid, and high labor-cost scenarios with explicit burden multipliers.",
"Positions burdened labor rates against CALC+ percentiles and sample sizes.",
"Calculates travel from GSA Per Diem data when travel is in scope.",
"Separates T&M materials from labor and applies supported material-handling costs.",
"Creates and validates seven-sheet xlsx workbooks with independent recomputation."
],
"limitations": [
"Requires BLS OEWS, GSA CALC+, and GSA Per Diem MCP services for complete sourced estimates.",
"Does not make fair-and-reasonable determinations or create T&M or LH Determination and Findings.",
"Does not support FFP, cost-reimbursement, grants, or cooperative agreements.",
"Cannot verify spreadsheet formula execution without Excel, LibreOffice, or another compatible engine."
],
"use_cases": [
{
"title": "Prepare an LH acquisition estimate",
"description": "Build labor scenarios, ceiling-hour comparisons, and source records for a structured Labor-Hour requirement.",
"target_user": "Federal contract specialist"
},
{
"title": "Estimate a T&M requirement",
"description": "Separate labor, travel, direct materials, and supported handling costs across base and option periods.",
"target_user": "Program manager"
},
{
"title": "Review proposed labor rates",
"description": "Compare proposed rates with BLS and CALC+ benchmarks using neutral statistics and documented sample sizes.",
"target_user": "Pricing analyst"
}
],
"prompt_templates": [
{
"title": "Build a basic LH estimate",
"prompt": "Build a Labor-Hour IGCE for [requirement] using [location], [labor categories], [FTE], [periods], [productive hours], and [burden basis].",
"scenario": "Use when contract type and staffing inputs are already defined."
},
{
"title": "Build a T&M estimate",
"prompt": "Build a T&M IGCE with [labor inputs], [travel], and [materials]. Show each cost stream separately and document all escalation assumptions.",
"scenario": "Use when reimbursable materials or travel are part of the contemplated contract."
},
{
"title": "Estimate from raw requirements",
"prompt": "Decompose this requirement into labor disciplines and candidate SOC mappings: [requirements]. Ask for Stage A confirmation before collecting the remaining estimate inputs.",
"scenario": "Use when staffing has not been structured or approved."
},
{
"title": "Position proposed rates",
"prompt": "Compare these proposed LH or T&M rates with BLS and CALC+ data: [rates]. Provide neutral positioning only and preserve my supplied conclusion verbatim.",
"scenario": "Use for advanced rate analysis without delegating the Contracting Officer's determination."
}
],
"output_examples": [
{
"input": "Build a three-year LH estimate for five cybersecurity analysts in Washington, DC.",
"output": "A seven-sheet workbook presents wage sources, burden scenarios, period totals, category ceiling hours, CALC+ comparisons, assumptions, and validation results."
},
{
"input": "Estimate a T&M support requirement with labor, travel, and cloud-hosting materials.",
"output": "The estimate separates burdened labor from travel and materials, applies independent escalation, records source dates, and identifies any unsupported handling cost."
},
{
"input": "Check whether proposed engineering rates are reasonable.",
"output": "The response first offers neutral positioning or a draft using the user's conclusion, then reports BLS and CALC+ comparisons without making a determination."
}
],
"best_practices": [
"Confirm LH or T&M before calculations and keep materials outside LH labor pricing.",
"Provide productive hours, ceiling hours, period dates, location, and the burden basis.",
"Review every source, assumption, formula-validation result, and disclosed data fallback."
],
"anti_patterns": [
"Do not treat the estimate total as the binding contract ceiling without confirmation.",
"Do not apply labor burden or arbitrary profit percentages to T&M materials.",
"Do not ask the skill to make legal, contract-type, or fair-and-reasonable determinations."
],
"faq": [
{
"question": "What contract types does this skill support?",
"answer": "It supports Labor-Hour and Time-and-Materials estimates. It does not support FFP or cost-reimbursement estimates."
},
{
"question": "Which data sources does it use?",
"answer": "It uses BLS OEWS wages, GSA CALC+ ceiling rates, and GSA Per Diem data when applicable."
},
{
"question": "Can it choose between LH and T&M?",
"answer": "No. The user must select the contemplated contract type after reviewing the structural difference."
},
{
"question": "Can it determine that proposed rates are fair and reasonable?",
"answer": "No. It provides neutral benchmark positioning or formats a draft from the Contracting Officer's supplied conclusion."
},
{
"question": "How are T&M materials handled?",
"answer": "Materials remain separate from labor. Handling indirects require a user-supplied accounting or solicitation basis."
},
{
"question": "How is the workbook validated?",
"answer": "The bundled validator audits structure and independently recomputes totals. LibreOffice can also execute formulas and verify cached values."
}
]
},
"file_structure": [
{
"name": "agents",
"type": "dir",
"path": "agents",
"children": [
{
"name": "openai.yaml",
"type": "file",
"path": "agents/openai.yaml",
"lines": 8
}
]
},
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "data-source-operations.md",
"type": "file",
"path": "references/data-source-operations.md",
"lines": 308
},
{
"name": "runtime-adaptation.md",
"type": "file",
"path": "references/runtime-adaptation.md",
"lines": 38
},
{
"name": "validation-gates.md",
"type": "file",
"path": "references/validation-gates.md",
"lines": 107
},
{
"name": "workbook-specification.md",
"type": "file",
"path": "references/workbook-specification.md",
"lines": 153
},
{
"name": "wrap-rate-presets.md",
"type": "file",
"path": "references/wrap-rate-presets.md",
"lines": 49
}
]
},
{
"name": "scripts",
"type": "dir",
"path": "scripts",
"children": [
{
"name": "recompute_expected_values.py",
"type": "file",
"path": "scripts/recompute_expected_values.py",
"lines": 211
},
{
"name": "validate_workbook.py",
"type": "file",
"path": "scripts/validate_workbook.py",
"lines": 547
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 232
},
{
"name": "test.md",
"type": "file",
"path": "test.md",
"lines": 70
},
{
"name": "testing.md",
"type": "file",
"path": "testing.md",
"lines": 366
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |