mechanism-audit

A review method for checking whether a written promise is actually enforced by code, configuration, tests, or operating procedures. It looks for gaps between what a specification says and what the system can really prevent or verify.

In plain words
What is it for?
Use it to audit agent instructions, safety boundaries, task workflows, build and test specifications, verification steps, and operational contracts.
Why use it?
It prevents teams from treating documentation as proof when a rule can still be bypassed or has no reliable check.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fiveonecode/agent-skills/mechanism-audit
Any agent
npx skills add fiveonecode/agent-skills --skill mechanism-audit
Clone the repo
git clone --depth 1 https://github.com/fiveonecode/agent-skills

Made for: Claude Code, Codex.

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00103 $0.00919
Opus 5 $0.00051 $0.00460
Sonnet 5 $0.00021 $0.00184
Haiku 4.5 $0.00010 $0.00092

Measured 3d ago against content hash dd9d650aa860, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mechanism-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 3d 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.

mechanism-audit/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mechanism Audit

Purpose

Use this skill to test whether a stated promise is enforced by code, config, verification, or operational process. Keep the audit short and evidence-led. Do not run a broad multi-expert swarm. This skill is safe to use from high or xhigh reasoning contexts because it is a bounded checklist, not a creativity prompt.

Inputs

Gather only the evidence needed to test the promise:

  • the promise or contract being audited
  • the files that define the rule
  • the code, config, or process that enforces it
  • the verification profile, test, artifact, or manual proof that checks it
  • the task/session context when the harness requires a durable audit artifact

If the promise is unclear, rewrite it as one testable sentence before auditing.

Audit Workflow

  1. Name the promise. State what the doc, task, or harness appears to guarantee. Use one sentence.
  2. Map the enforcement chain. List the concrete files, commands, checks, code paths, review gates, or artifacts that make the promise true.
  3. Find bypass paths. Look for ways the promise can be skipped, narrowed, stale, manually overridden, or satisfied by prose instead of proof.
  4. Check verification. Decide whether the current tests, verifier profiles, required evidence, or closeout gates would catch the bypass paths.
  5. Give a verdict. Use exactly one of:
    • holds
    • partially holds
    • does not hold
    • not enough evidence
  6. List fixes. Use:
    • P0 for fixes required before the guarantee should stand
    • P1 for robustness improvements that strengthen an already plausible guarantee

Output Shape

Use this format:

Promise:
- <one testable sentence>

Enforcement chain:
- <file/code/config/process evidence>

Bypass paths:
- <specific bypass or "none found">

Verification coverage:
- <what is checked and what is not checked>

Verdict:
- <holds | partially holds | does not hold | not enough evidence>

Fixes:
- P0: <required fix, or "none">
- P1: <strengthening fix, or "none">

Read the full file on GitHub · 118 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 3d ago First seen · 118 lines · 103 tokens per session scan A dd9d650aa860

Subscribe to this mod's changes

mechanism-audit is a skill published in the GitHub repository fiveonecode/agent-skills (19 stars, last pushed 11d ago), licensed MIT. It adds 103 tokens to every session and 919 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens