Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mushroomTW/MushroomTW-Skills --skill repository-bug-auditgit clone --depth 1 https://github.com/mushroomTW/MushroomTW-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mushroomtw/mushroomtw-skills/repository-bug-audit)<a href="https://agentmods.dev/skills/mushroomtw/mushroomtw-skills/repository-bug-audit"><img src="https://agentmods.dev/badge/skills/mushroomtw/mushroomtw-skills/repository-bug-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mushroomtw/mushroomtw-skills/repository-bug-audit"><img src="https://agentmods.dev/badge/skills/mushroomtw/mushroomtw-skills/repository-bug-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00109 | $0.01798 |
| Opus 5 | $0.00055 | $0.00899 |
| Sonnet 5 | $0.00022 | $0.00360 |
| Haiku 4.5 | $0.00011 | $0.00180 |
Grade A, and why
repository-bug-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Bug Audit
Audit the current working tree by finding material bugs first, then assess broader engineering quality in Comprehensive mode. Deliver exactly one artifact: a concise Markdown report. The evidence JSON behind it is a validation input, deleted when the run ends. Remain read-only except for those two files.
Required startup choices
The one choice is audit mode — Rapid (map whole repo, read core/high-risk paths, only defect/risk, no score) or Comprehensive (read every in-scope file, all three finding types, 0–100 score). Execution mode is fixed: Multi-agent partitioned (one subagent per partition, cross-reviews High findings; see platform-adapters).
🔴 CHECKPOINT — Obtain confirmation for the choice before entering Workflow: Ask in one interaction (skip what the user already stated). Follow platform-adapters for the host's choice UI. If Multi-agent is unavailable, explain and 🛑 STOP — never silently fall back or downgrade to a single-agent run.
Workflow
- Select modes — In: user request; Out:
audit_mode+review_mode=multi-agent; Format: singleAskUserQuestion(skip if already answered). - Build map & inventory — In:
AGENTS.md/README/manifests/CI; Out:inventory[](path,status,risk_tier,reason); Entire working tree, never usegit diff/history. - Trace flows — In:
core|highitems; Out:core_flows[](name,entry_point,status,evidence[]); Every known core/high must be traced. - Run checks — In: configured commands; Out:
verification_checks[](status=passed|failed|not_run|unavailable); Never install tools/write probes;reproducedonly from executed configured checks. - Write evidence — In:
schema.json+audit-protocol.md §1,2,5; Out:.docs/<report-stem>.evidence.json(12 required fields), a validation input only; Never include secrets/full sources. - Write report — In: evidence; Out:
.docs/<report>.mdexactly 4 sections (§4), render severity as🔴/🟡/🟢, do not copy JSON. - Validate & fix — In: the validator command in Validate and deliver; Out: exit 0/1/2; Fix, delete the evidence file, then return the report link + summary, never paste full artifacts.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed 8d042c1aa5c2
- 11d ago First seen · 85 lines · 109 tokens per session scan A 4bf4e0ebbfa3
repository-bug-audit is a skill published in the GitHub repository mushroomTW/MushroomTW-Skills (0 stars, last pushed 11d ago), licensed MIT. It adds 109 tokens to every session and 1,798 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
working-effectively-with-legacy-code
Apply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.
refactoring
Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.
truecourse-fix
Fix TrueCourse violations that have suggested fixes.