yasdef-worker-ai-audit

yasdef-worker-ai-audit is a skill for Claude Code, Codex from yasdef/yasdef-core. It costs 61 tokens per session (1,627 once invoked), scanned A, original, MIT.

A YASDEF review workflow that audits one development step after user review. It checks whether the current code changes prove the step's requirements and records what happens to each finding.

In plain words
What is it for?
Use it to inspect a step's patch, record findings, classify each finding as followed up, escalated, or rejected, and complete the audit handoff.
Why use it?
It identifies gaps between the requested step and the delivered changes before the work is closed. The audit is analysis-only and does not modify runtime code or run tests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions AGENTS.md.

Good fit Use it to inspect a step's patch, record findings, classify each finding as followed up, escalated, or rejected, and complete the audit handoff.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yasdef/yasdef-core/yasdef-worker-ai-audit
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.

Any agent
npx skills add yasdef/yasdef-core --skill yasdef-worker-ai-audit
Clone the repo
git clone --depth 1 https://github.com/yasdef/yasdef-core

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for yasdef-worker-ai-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/yasdef/yasdef-core/yasdef-worker-ai-audit/github.svg)](https://agentmods.dev/skills/yasdef/yasdef-core/yasdef-worker-ai-audit)
Your own site
<a href="https://agentmods.dev/skills/yasdef/yasdef-core/yasdef-worker-ai-audit"><img src="https://agentmods.dev/badge/skills/yasdef/yasdef-core/yasdef-worker-ai-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.

agentmods 80×15 button for yasdef-worker-ai-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/yasdef/yasdef-core/yasdef-worker-ai-audit"><img src="https://agentmods.dev/badge/skills/yasdef/yasdef-core/yasdef-worker-ai-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00061 $0.01627
Opus 5 $0.00030 $0.00813
Sonnet 5 $0.00012 $0.00325
Haiku 4.5 $0.00006 $0.00163

Measured 11d ago against content hash 944593726666, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

yasdef-worker-ai-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 11d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/append_follow_up_step.py, scripts/build_ai_audit_context.py, scripts/check_ai_audit_closure.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/yasdef_worker/_data/skills/yasdef-worker-ai-audit/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YASDEF Worker AI Audit

Use this skill for the ASDLC worker ai_audit phase. This phase is analysis-only: do not modify runtime code and do not run tests.

Inputs

The yasdef prompt should provide:

  • step id, for example 1.6
  • feature id
  • branch name
  • step plan path
  • design artifact path
  • runtime implementation plan path
  • worker id

If any input is missing, inconsistent, or points to a missing required file, do not infer it from .asdlc_worker/feature_meta_sync.yaml or the runtime environment. Stop and ask the user for explicit instructions.

Phase Contract

  • Analysis-only: do not modify runtime code and do not run tests.
  • Audit question: for this step, are all target bullets proven by the current patch; if not, identify the concrete gaps that remain.
  • Two-phase model: Phase 1 discovery is a single pass; Phase 2 disposition is a mechanical loop over all findings.
  • Terminal states per finding: follow_up_created, raised_to_coordinator, or rejected.
  • Commit boundary: commit worker review-result changes only; leave ASDLC edits uncommitted for post_review.
  • Completion protocol: run check_ai_audit_closure.py before the completion lines.

Workflow

  1. Run the entry gate as the first action:

    uv run python .claude/skills/yasdef-worker-ai-audit/scripts/check_ai_audit_entry.py --step <step> --feature-id <feature-id>
    

    If it exits non-zero, stop and report the failed preconditions.

  2. Build context:

    uv run python .claude/skills/yasdef-worker-ai-audit/scripts/build_ai_audit_context.py --step <step> --feature-id <feature-id> --design <design-file> --runtime-plan <runtime-plan> --worker-id <worker-id>
    
  3. Read the printed context before reviewing. The step design artifact is the single context source. Use only:

  • ## Target Bullets (excluding planning/review)
  • ## Selected EARS Requirements (for planning translation)
  • ## Goal
  • ## In Scope
  • ## Out of Scope
  • ## Linked Artifacts (in scope)
  1. Phase 1 - Discovery (single pass):
  • Review the current patch via git status and git diff.
  • Write all findings in one pass to step_review_results/review_result-<step>-<feature>.md.
  • Each finding must include severity, recommendation (FollowupStep or RiseToCoordinator), reasoning, references, and a three-state checkbox block:
    • follow_up_created
    • raised_to_coordinator
    • rejected
  • Initialize all three state checkboxes unchecked.
  • Do not start disposition before all findings are written.

Read the full file on GitHub · 121 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. 11d ago First seen · 121 lines · 61 tokens per session scan A 944593726666

Subscribe to this mod's changes

yasdef-worker-ai-audit is a skill published in the GitHub repository yasdef/yasdef-core (5 stars, last pushed 24d ago), licensed MIT. It adds 61 tokens to every session and 1,627 once invoked, about $0.0003 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

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens