Adonis0123/adonis-skills / skills/dev-environment-roi-audit
dev-environment-roi-audit
VerifiedAudit a local coding-agent environment with real logs and controlled ablations, then make evidence-backed keep, narrow, on-demand, or remove decisions for MCP servers, skills, instruction files, plugins, commands, hooks, and memory, plus the attention they cost the user (notifications, pending decisions, scheduled automations, and settings toggles). Use whenever the user asks to audit or slim a Claude, Codex, Grok, Cursor, or similar development setup; find unused tools; quantify context, startup, or attention tax; review noisy notifications or scheduled jobs; or clean agent configuration by ROI. Enforces discovered paths, per-file JSONL schema probes, OUT_DIR-only artifacts, secret-safe output, and item-by-item approval before mutations.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.3 KB |
| evals/evals.json | config | 2.3 KB |
| evals/fixtures/schema-a.jsonl | other | 72 B |
| evals/fixtures/schema-b.jsonl | other | 151 B |
| references/artifact-contract.md | markdown | 2.2 KB |
| references/metrics-and-decisions.md | markdown | 5.5 KB |
| scripts/finalize_audit.pyexecutable | script | 2.4 KB |
| scripts/init_audit.pyexecutable | script | 2.0 KB |
| scripts/probe_jsonl_schema.pyexecutable | script | 2.6 KB |
references/artifact-contract.md
View on GitHub# Artifact and interaction contract
## Required outputs
All artifacts live under the agreed absolute `OUT_DIR`.
| Path | Purpose |
|---|---|
| `00-capabilities.json` | CLI versions, utility availability, wrappers, blocked flags |
| `01-inventory.json` | Pure component and cost-side data |
| `02-metrics.json` | Machine-readable M1-M11 metrics |
| `02-metrics.md` | Human-readable metrics and tables |
| `03-experiments.md` | Experiments plus sanitized raw output |
| `dispatch-prompt.md` | Blind-review prompt, when used |
| `04-*.json` / `04-*.jsonl` | Independent reviewer output and events |
| `FINAL.md` | Decisions, bills, conflicts, disagreements, guards, unknowns |
| `scripts/` | Every parser/helper needed to reproduce the audit |
| `raw/` | Sanitized command and probe output |
| `runtime/` | Reproducible caches, isolated homes, clones, and experiment state |
| `proposed/` | Draft config/instruction changes only |
| `recovery/` | Minimal credential-free recovery fragments |
| `MANIFEST.sha256` | Integrity for non-runtime artifacts |
## Command checkpoint format
Before a command, state:
```text
要跑:<command purpose>
想得到:<specific numeric fields>
写入:<OUT_DIR paths or “none”>
```
After a command, present:
```text
原始输出:<relevant unedited/sanitized lines>
解释:<what the numbers establish>
下一步:<one bounded action>
```
Do not hide a failed command. Show the error, explain whether it invalidates a metric, and inspect `--help` only after the failure.
## Resume behavior
- Treat inventory and metrics as timestamped snapshots, not current truth.
- On resume, verify current config and source paths before acting on an old recommendation.
- Never overwrite a raw artifact silently. Use a dated suffix or record that a file is a refreshed current-state artifact.
- A historical call count remains historical after a component is removed.
## Output hygiene
- Sanitize tokens, cookies, Authorization values, emails, private prompts, and personal data before writing.
- It is safe to record credential field names, value types, string lengths, and counts.
- Do not include raw session content when aggregated tool names and counts are enough.
- Keep reports small; remove reproducible runtime clones after embedding necessary evidence.
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: 471k | 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: 471k | 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: 471k | 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 |