Skip to content

notque/vexjoy-agent / skills/meta/toolkit

toolkit

Verified

Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.

FileKindSize
SKILL.mdskill md15.5 KB
agents/skill-creator/analyzer.mdmarkdown4.8 KB
agents/skill-creator/comparator.mdmarkdown4.7 KB
agents/skill-creator/grader.mdmarkdown3.9 KB
assets/skill-creator/eval_viewer.htmlother57.1 KB
references/agent-comparison.mdmarkdown11.5 KB
references/agent-comparison/benchmark-tasks.mdmarkdown6.8 KB
references/agent-comparison/do-creation-compliance-tasks.jsonconfig8.5 KB
references/agent-comparison/examples-and-errors.mdmarkdown1.0 KB
references/agent-comparison/grading-rubric.mdmarkdown4.3 KB
references/agent-comparison/methodology.mdmarkdown7.4 KB
references/agent-comparison/optimization-guide.mdmarkdown12.0 KB
references/agent-comparison/optimization-tasks.example.jsonconfig853 B
references/agent-comparison/optimize-phase.mdmarkdown9.3 KB
references/agent-comparison/read-only-ops-short-tasks.jsonconfig375 B
references/agent-comparison/report-template.mdmarkdown3.8 KB
references/agent-comparison/socratic-debugging-body-short-tasks.jsonconfig372 B
references/agent-comparison/socratic-debugging-trigger-tasks.jsonconfig2.8 KB
references/agent-creator.mdmarkdown10.9 KB
references/agent-creator/agent-design-patterns.mdmarkdown12.4 KB
references/agent-creator/agent-eval-design.mdmarkdown7.7 KB
references/agent-creator/agent-frontmatter-template.mdmarkdown9.3 KB
references/agent-evaluation.mdmarkdown10.6 KB
references/agent-evaluation/batch-evaluation.mdmarkdown1.6 KB
references/agent-evaluation/common-issues.mdmarkdown2.1 KB
references/agent-evaluation/report-templates.mdmarkdown2.2 KB
references/agent-evaluation/scoring-rubric.mdmarkdown2.4 KB
references/blind-ab-tests.mdmarkdown7.8 KB
references/generate-claudemd.mdmarkdown11.0 KB
references/generate-claudemd/CLAUDEMD_TEMPLATE.mdmarkdown4.1 KB
references/generate-claudemd/examples-and-errors.mdmarkdown7.4 KB
references/github-profile-rules.mdmarkdown7.5 KB
references/github-profile-rules/github-api-patterns.mdmarkdown8.2 KB
references/github-profile-rules/rule-categories.mdmarkdown4.8 KB
references/hook-development.mdmarkdown10.9 KB
references/hook-development/architecture.mdmarkdown3.7 KB
references/hook-development/code-examples.mdmarkdown9.4 KB
references/hook-development/preferred-patterns.mdmarkdown6.5 KB
references/hook-development/telemetry-database.mdmarkdown6.5 KB
references/routing-table-updater.mdmarkdown10.2 KB
references/routing-table-updater/batch-mode.mdmarkdown2.1 KB
references/routing-table-updater/conflict-resolution.mdmarkdown3.8 KB
references/routing-table-updater/error-handling.mdmarkdown1.9 KB
references/routing-table-updater/examples.mdmarkdown4.8 KB
references/routing-table-updater/extraction-patterns.mdmarkdown2.2 KB
references/routing-table-updater/routing-format.mdmarkdown3.6 KB
references/routing-table-updater/skill-examples.mdmarkdown2.7 KB
references/skill-composer.mdmarkdown9.1 KB
references/skill-composer/compatibility-matrix.mdmarkdown13.0 KB
references/skill-composer/composition-patterns.mdmarkdown4.9 KB
references/skill-composer/examples.mdmarkdown17.1 KB
references/skill-composer/skill-patterns.mdmarkdown12.5 KB
references/skill-creator.mdmarkdown28.9 KB
references/skill-creator/agent-template.mdmarkdown18.5 KB
references/skill-creator/artifact-schemas.mdmarkdown8.2 KB
references/skill-creator/bundled-components.mdmarkdown2.3 KB
references/skill-creator/complexity-tiers.mdmarkdown8.0 KB
references/skill-creator/domain-research-targets.mdmarkdown13.2 KB
references/skill-creator/enrichment-workflow.mdmarkdown9.9 KB
references/skill-creator/error-catalog.mdmarkdown9.9 KB
references/skill-creator/preferred-patterns.mdmarkdown11.7 KB
references/skill-creator/progressive-disclosure.mdmarkdown8.5 KB
references/skill-creator/skill-template.mdmarkdown14.6 KB
references/skill-creator/workflow-patterns.mdmarkdown7.6 KB
references/system-upgrade.mdmarkdown11.0 KB
references/system-upgrade/component-audit-checklists.mdmarkdown8.4 KB
references/system-upgrade/upgrade-failure-modes.mdmarkdown8.7 KB
references/system-upgrade/upgrade-signal-parsing.mdmarkdown7.3 KB
references/toolkit-evolution.mdmarkdown14.5 KB
references/toolkit-evolution/diagnose-scripts.mdmarkdown9.5 KB
references/toolkit-evolution/evolution-history.mdmarkdown5.5 KB
references/toolkit-evolution/evolution-report-template.mdmarkdown716 B
references/toolkit-evolution/evolve-preferred-patterns.mdmarkdown6.9 KB
references/toolkit-evolution/evolve-scripts.mdmarkdown3.7 KB
references/toolkit-governance.mdmarkdown16.0 KB
references/toolkit-governance/adr-lifecycle.mdmarkdown10.9 KB
references/toolkit-governance/frontmatter-compliance.mdmarkdown11.1 KB
references/toolkit-governance/hook-standardization.mdmarkdown21.5 KB
references/toolkit-governance/routing-table-patterns.mdmarkdown11.6 KB
references/weak-model-uplift.mdmarkdown10.3 KB
scripts/agent-comparison/compare.pyscript2.3 KB
scripts/agent-comparison/generate_variant.pyscript19.6 KB
scripts/agent-comparison/optimize_loop.pyscript89.3 KB
scripts/agent-comparison/trigger_eval.pyscript19.5 KB
scripts/routing-table-updater/extract_metadata.pyscript10.8 KB
scripts/routing-table-updater/generate_routes.pyscript10.5 KB
scripts/routing-table-updater/scan.pyscript4.7 KB
scripts/routing-table-updater/update_routing.pyscript12.4 KB
scripts/routing-table-updater/validate.pyscript7.3 KB
scripts/skill-composer/build_dag.pyscript12.5 KB
scripts/skill-composer/discover_skills.pyscript12.1 KB
scripts/skill-composer/validate.pyscript12.3 KB
scripts/skill-creator/aggregate_benchmark.pyscript10.0 KB
scripts/skill-creator/eval_compare.pyscript10.2 KB
scripts/skill-creator/optimize_description.pyscript12.5 KB
scripts/skill-creator/package_results.pyscript7.8 KB
scripts/skill-creator/run_eval.pyscript6.3 KB

references/toolkit-governance/adr-lifecycle.md

View on GitHub
# ADR Lifecycle Reference

> **Scope**: ADR status transitions, validation criteria, consultation records, and local-only governance. Does not cover routing tables or frontmatter compliance (see sibling reference files).
> **Version range**: all toolkit versions
> **Generated**: 2026-04-15

---

## Overview

ADRs are local working documents that track architectural decisions. They live in `adr/` (gitignored) and never get committed. The lifecycle moves through four states: `Proposed → Accepted → Implemented → Superseded`. Skipping a state is a governance violation — a `Proposed` ADR should not jump directly to `Implemented` without explicit `Accepted` confirmation, because that bypasses the consultation record and validation criteria.

---

## Status Transition Table

| From | To | Required Before Transitioning | Common Skip Error |
|------|----|-------------------------------|-------------------|
| `Proposed` | `Accepted` | Decision documented, alternatives listed, consultation complete | Moving to Implemented before acceptance |
| `Accepted` | `Implemented` | Validation criteria written, implementation verified against them | Marking implemented before criteria are met |
| `Implemented` | `Superseded` | New ADR number referenced, rationale for supersession documented | Deleting instead of superseding |
| Any | `Rejected` | Rejection reason documented, alternatives noted | Silently deleting instead of rejecting |

---

## ADR File Format

```markdown
# ADR-NNN: Title

## Status
Proposed — YYYY-MM-DD

## Date
YYYY-MM-DD

## Context
[Why this decision is needed. What problem it solves. Constraints.]

## Decision
[What was decided. Be specific enough that "Implemented" can be verified.]

## Alternatives Considered
[What else was considered and why it was rejected. Required for Accepted status.]

## Validation Criteria
[Concrete, checkable criteria that prove implementation is complete.]
[Required before transitioning Accepted to Implemented.]

## Consultation Notes
[Records from assessment sessions. Required for contested decisions.]

## Consequences
[What changes because of this decision. Positive and negative.]
```

---

## Correct Patterns

### Status Line Format

The status line must include the state word and the date.

```markdown
## Status
Proposed — 2026-04-15

## Status
Accepted — 2026-04-15. [Optional one-line summary of acceptance condition.]

## Status
Implemented — 2026-04-15. Validation: all 3 criteria met (see criteria section).

## Status
Superseded — 2026-04-15. Superseded by ADR-NNN.

## Status
Rejected — 2026-04-15. [One-line reason.]
```

**Why**: The date is required for time-ordered audit trails. `scripts/adr-status.py` parses the date to compute ADR age and flag stale proposed items.

---

### Validation Criteria Before Implementing

Write concrete, falsifiable criteria in `Accepted` state before marking `Implemented`.

```markdown
## Validation Criteria
- [ ] `python3 scripts/new-feature.py --check` exits 0
- [ ] `grep -r "old-pattern" agents/ skills/` returns no matches
- [ ] At least one existing test exercises the new path
- [ ] INDEX.json regenerated and coverage count unchanged
```

**Why**: Vague criteria ("feature works") cannot be objectively verified. Concrete criteria make `Implemented` status auditable — anyone reading the ADR can confirm implementation without re-investigating.

---

### Consultation Records

When `assessment` is dispatched, record its output in the ADR.

```markdown
## Consultation Notes
### 2026-04-15 — assessment run
Challenger raised: "This breaks existing consumers if they rely on field ordering."
Resolution: Field ordering is not guaranteed by the spec — confirmed in docs/PHILOSOPHY.md §3.
Decision unchanged.
```

**Why**: Consultation records prevent re-litigating decisions. If the same objection appears later, the ADR shows it was already considered and explains why it was resolved that way.

---

## Pattern Catalog
<!-- no-pair-required: section header with no content -->

### Include Accepted Step Before Implementing

**Detection**:
```bash
# Find Implemented ADRs that lack a prior Accepted state record
grep -rn "Implemented" adr/*.md | cut -d: -f1 | sort -u | xargs grep -L "Accepted"

# Find Implemented ADRs missing Validation Criteria section
grep -rn "Implemented" adr/*.md | cut -d: -f1 | sort -u | xargs grep -L "Validation Criteria"
```

**Signal**: <!-- no-pair-required: sub-block split by code-comment heading; Do instead is inline below -->
```markdown
## Status
Implemented — 2026-04-15
# (no Accepted state, no Validation Criteria section)
```

**Preferred action:** Add an explicit `Accepted` state before `Implemented`. See the positive guidance below.

**Why this matters**: Skipping `Accepted` means the decision was never formally reviewed and alternatives were never documented. `Implemented` status becomes meaningless — it cannot be distinguished from "I started writing code" versus "all criteria verified."

**Preferred action:**

Add an explicit `Accepted` state with a completed `## Alternatives Considered` section and a checkable `## Validation Criteria` section before moving to `Implemented`. Run `grep -L "Accepted" adr/*.md` to find ADRs that skipped this step.

**Preferred action**: Add an `Accepted` block with alternatives and validation criteria, then re-evaluate whether `Implemented` is truly warranted.

---

### Supersede or Reject ADRs, Never Delete

**Detection**:
```bash
# Gaps in ADR numbering indicate deletions
python3 -c "
import glob, re, os
nums = []
for f in glob.glob('adr/*.md'):
    m = re.search(r'(\d+)-', os.path.basename(f))
    if m: nums.append(int(m.group(1)))
nums.sort()
if nums:
    gaps = [i for i in range(nums[0], nums[-1]+1) if i not in nums]
    if gaps: print('GAPS (possible deletions):', gaps)
    else: print('No numbering gaps found')
"
```

**Why this matters**: Deleting an ADR erases the decision history. Future contributors cannot tell whether a feature was rejected (do not implement it) or just never decided (still open). The absence looks like a gap in thinking rather than a deliberate choice.

**Preferred action:**

Set the status to `Rejected — YYYY-MM-DD. [one-line reason]` or `Superseded — YYYY-MM-DD. Superseded by ADR-NNN.` The file stays in `adr/` permanently. Run the numbering-gap detection script to find any ADRs that were already deleted and document the gap.

**Preferred action**: Set status to `Rejected — YYYY-MM-DD. [reason]` or `Superseded — YYYY-MM-DD. Superseded by ADR-NNN.` Never delete.

---

### Include Date in Every Status Line

**Detection**:
```bash
# Find status lines without em-dash and date
grep -n "^## Status" adr/*.md -A1 | grep -v " — [0-9]\|^adr\|^--\|^$"

# Alternative: find Proposed/Accepted/Implemented lines missing date pattern
grep -rn "^Proposed\|^Accepted\|^Implemented\|^Superseded\|^Rejected" adr/*.md | grep -v " — 20[0-9][0-9]-"
```

**Signal**: <!-- no-pair-required: sub-block split by code-comment heading; Do instead is inline below -->
```markdown
## Status
Implemented
```

**Preferred action:** Always append ` — YYYY-MM-DD` to every status line. See the positive guidance below.

**Why this matters**: `scripts/adr-status.py` parses the date from the status line to compute age and detect stale proposals. Missing dates silently break age-based reporting and make the audit trail unreliable.

**Preferred action:**

Always write the full status line: `Proposed — YYYY-MM-DD` (or `Accepted`, `Implemented`, `Superseded`, `Rejected`). Use the detection command `grep -rn "^Proposed\|^Accepted\|^Implemented" adr/*.md | grep -v " — 20"` to find lines missing the date.

**Preferred action**: Always append ` — YYYY-MM-DD` to every status line.

---

### Write Validation Criteria During Accepted Phase

**Signal**:
Criteria written in future tense ("will verify", "should check") or added to the ADR after the `Implemented` date stamp.

**Preferred action:** Write criteria in present-tense checkboxes during the `Accepted` phase, before any implementation begins. See the positive guidance below.

**Detection**:
```bash
# Find criteria using future tense (indicative of post-hoc writing)
grep -rn "will verify\|should check\|to be verified\|TBD" adr/*.md
```

**Why this matters**: Validation criteria written after the fact are retroactive justifications, not pre-agreed standards. They cannot prove the implementation met a standard that didn't exist when work was done.

**Preferred action:**

Write validation criteria as present-tense checkboxes in the `## Validation Criteria` section while the ADR is in `Accepted` state. Each criterion must be falsifiable: a specific command to run or a specific condition to check. Only mark `Implemented` after every checkbox is confirmed.

**Preferred action**: Write criteria in present tense as checkboxes during the `Accepted` phase. Mark each criterion complete only when verified during implementation.

---

## Error-Fix Mappings

| Symptom | Root Cause | Fix |
|---------|------------|-----|
| `scripts/adr-status.py` cannot parse status date | Missing ` — YYYY-MM-DD` in status line | Add date in `Status — YYYY-MM-DD` format |
| ADR shows as "stale" in status report | Status is Proposed and last modified >30 days ago | Advance status or add a hold note explaining delay |
| Consultation rejected but decision still advanced | No consultation record in ADR body | Add consultation notes section with objection and resolution |
| ADR not found by `adr-status.py` | Filename doesn't match `NNN-kebab-title.md` pattern | Rename to match; script scans by glob pattern |
| `grep -L "Alternatives"` returns this ADR | Accepted without listing alternatives | Add `## Alternatives Considered` section before re-advancing |

---

## Detection Commands Reference

```bash
# List all ADRs with their current status
grep -h "^## Status" adr/*.md -A1 | grep -v "^## Status\|^--"

# Find Proposed ADRs older than 30 days (stale proposals)
python3 -c "
import glob, re
from datetime import datetime
for f in glob.glob('adr/*.md'):
    txt = open(f).read()
    m = re.search(r'Proposed — (\d{4}-\d{2}-\d{2})', txt)
    if m:
        age = (datetime.now() - datetime.strptime(m.group(1), '%Y-%m-%d')).days
        if age > 30: print(f'STALE ({age}d): {f}')
"

# Find Implemented ADRs missing Validation Criteria
grep -rn "Implemented" adr/*.md | cut -d: -f1 | sort -u | xargs grep -L "Validation Criteria"

# Find ADRs missing Alternatives Considered (required for Accepted+)
grep -rL "Alternatives" adr/*.md

# Find status lines without date
grep -rn "^Proposed\|^Accepted\|^Implemented\|^Superseded\|^Rejected" adr/*.md | grep -v " — 20"

# Find validation criteria with future tense (post-hoc writing)
grep -rn "will verify\|should check\|to be verified" adr/*.md
```

---

## See Also

- `routing-table-patterns.md` — INDEX.json validation, component registration
- `frontmatter-compliance.md` — YAML field compliance for agents and skills
- `docs/PHILOSOPHY.md` — deterministic validation and anti-rationalization principles
- `scripts/adr-status.py` — CLI for ADR status reporting and intake queue
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall