audit-impl

A final review tool for a completed implementation that compares the changed code with its original plan or plans. It returns either GO for approval to merge or NO GO with a remediation file describing required fixes.

In plain words
What is it for?
Use it after implementation and tests, on a plan file, a group of plans, or a campaign manifest, to make a merge decision.
Why use it?
It helps catch missed requirements, unintended changes, and work outside the agreed scope before code is merged.

Skill for Claude CodeCodex

Part of the autoskillit plugin — 36 skills, 1 MCP server shipped together

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/talont-org/autoskillit/audit-impl
Any agent
npx skills add TalonT-Org/AutoSkillit --skill audit-impl
Clone the repo
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit

Made for: Claude Code, Codex.

Or install autoskillit, the plugin that ships this one along with the rest of its 36 skills, 1 MCP server.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,646 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 $0.00040 $0.03646
Opus 5 $0.00020 $0.01823
Sonnet 5 $0.00008 $0.00729
Haiku 4.5 $0.00004 $0.00365

Measured 3d ago against content hash f55fc7c32fad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-impl 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.

src/autoskillit/skills_extended/audit-impl/SKILL.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Audit Skill

Audit a completed implementation against its plan(s) before merge. Identifies gaps, missed requirements, scope creep, and unexpected changes. Produces a GO or NO GO verdict.

When to Use

  • After implementation completes and tests pass, as the last step before merging
  • In single-plan pipelines: audit the worktree against the plan
  • In multi-group pipelines: audit the feature branch against all group plans via manifest
  • Standalone: /autoskillit:audit-impl {plans_input} {branch_name} {base_branch}

Arguments

{plans_input} {branch_name} {base_branch} [conflict_report_paths]
  • plans_input — one of:
    • A single plan .md file path
    • A comma-separated list of .md plan file paths (no spaces around commas)
    • A directory containing *_plan_*.md files
    • A manifest_*.json from /autoskillit:make-groups
  • branch_name — commit SHA of the pre-implementation base ref (preferred from pipeline, stable after merge_worktree destroys named refs); a branch name is also accepted for standalone invocations. A live worktree path is accepted for legacy use (Step 0 extracts the branch name automatically).
  • base_branch — branch to diff against (default: develop)
  • conflict_report_paths (optional) — comma-separated list of absolute paths to conflict resolution reports produced by resolve-merge-conflicts. When provided and non-empty, cross-reference resolution decisions against plan intent in Step 2.5.

Critical Constraints

NEVER:

  • Modify source files, plan files, or any other files — read-only audit only
  • Run tests — this skill audits, it does not fix
  • Create files outside {{AUTOSKILLIT_TEMP}}/audit-impl/
  • Emit a GO verdict when any MISSING or CONFLICT finding exists
  • Run subagents in the background (run_in_background: true is prohibited)

ALWAYS:

  • Use Explore subagents for all file reads and diff retrieval
  • Use model: "sonnet" when spawning all subagents via the Task tool
  • Resolve all plan files before starting (abort early if any are missing)
  • Write Dry-walkthrough verified = TRUE as the absolute first line of any remediation file
  • On a NO GO verdict, after writing the remediation file, emit the absolute path as a structured output token as your final output. Resolve the relative temp/audit-impl/... save path to absolute by prepending the full CWD:
    verdict = NO GO
    remediation_path = /absolute/cwd/temp/audit-impl/{filename}.md
    
    On a GO verdict, emit only verdict = GO (no remediation_path token). The remediation_path token is MANDATORY on NO GO — the pipeline cannot proceed without it.

Read the full file on GitHub · 371 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 · 371 lines · 40 tokens per session scan A f55fc7c32fad

Subscribe to this mod's changes

audit-impl is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 3,646 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

007

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

sickn33/agentic-awesome-skills · 39 tokens

edgeone-clawscan

The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Lab. Works like an antivirus for your AI environment: audits installed skills, scans skills before installation, and performs a full OpenClaw security health check to prevent data leaks and privacy risks. Backed by Tencent Zhuque…

Tencent/AI-Infra-Guard · 236 tokens

edgeone skill scanner

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…

Tencent/AI-Infra-Guard · 148 tokens

analyzing-ethereum-smart-contract-vulnerabilities

Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.

mukul975/Anthropic-Cybersecurity-Skills · 49 tokens

agent-review

Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.

stencila/stencila · 57 tokens

skill-review

Critically review a workspace skill and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve a SKILL.md file or skill directory. Covers frontmatter validation, instruction clarity, completeness, and adherence to the Agent Skills Specification.

stencila/stencila · 54 tokens