audit

A structured comparison process for finding differences between two existing implementations, systems, or specifications.

In plain words
What is it for?
Checking feature parity, comparing old and new systems, verifying an implementation against a specification, and flagging missing or changed parts.
Why use it?
It reduces the chance that a new version is missing behavior or details from the reference version.

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

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00104 $0.01091
Opus 5 $0.00052 $0.00545
Sonnet 5 $0.00021 $0.00218
Haiku 4.5 $0.00010 $0.00109

Measured 3d ago against content hash e512f40ebf64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit scanned grade A with 1 finding 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat .claude/audit-config.md 2>/dev/null || true`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

platforms/codex/plugin/skills/audit/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Comparison Audit

Routing overlap? If this intent better matches a sibling skill, redirect per references/routing-tiebreaks.md (prefer implementation parity over prose doc alignment).

Project Audit Config

!cat .claude/audit-config.md 2>/dev/null || true

Key Concepts

Term Definition
Source The spec, old system, or canonical implementation -- the "source of truth"
Target The new system or implementation being audited
Parity Target covers all source capabilities correctly
By-Design Intentional divergence between source and target

Methodology

Phase 1: Define Scope

Establish before exploring code:

  1. What is the Source (reference)?
  2. What is the Target (audited)?
  3. What constitutes parity? (functional equivalence | field completeness | behavioral match)
  4. What differences are known By-Design?
Target-exists precondition (hard routing gate)

Resolve both Source and Target to concrete artifacts before comparing them. The Target must be an already-existing implementation/system/code path, not a feature described only in a future plan. The current repository as a whole is not a substitute for a missing future target.

If the Target does not exist, stop before Phase 2 and return:

status: routing_precondition_failed
reason: parity audit requires an existing target implementation
route: plan-readiness reviewer

Repository code may verify factual premises in a plan, but its absence of the planned future feature is not a parity finding.

Phase 2: Parallel Exploration

Split into segments (Entry/Init, Core Ops, Edge Cases, Post-Op, Field Completeness). For each, compare presence, correctness, completeness. Spawn one agent per segment for large audits.

Re-dispatch on the same segment after a fix follows the blind discipline — see Phase 4 below and references/blind-dispatch.md. First-pass exploration is full-context by design; only verification passes are blinded.

Read the full file on GitHub · 90 lines

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 · 90 lines · 104 tokens per session scan A e512f40ebf64

Subscribe to this mod's changes

audit is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 3d ago), licensed MIT. It adds 104 tokens to every session and 1,091 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). 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