audit-judgment

audit-judgment is a skill for Claude Code from xiaolai/eou-foundry. It costs 89 tokens per session (2,157 once invoked), scanned A, original, ISC.

An audit procedure for checking an agent's recorded value decisions against an authorized workflow and defined failure rules. It also checks for decision drift, invented value identifiers, and missing decisions on disputed cases.

In plain words
What is it for?
Use it to audit value invocations for EOUs marked as allowing agent judgment, together with the relevant workflow, run traces, rules, and prior audits.
Why use it?
It helps verify that judgment calls recorded in a run were allowed, consistent, and fully documented.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: $skill-name invocation.

Part of the eou-foundry plugin — 14 skills, 1 command 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/xiaolai/eou-foundry/audit-judgment
Any agent
npx skills add xiaolai/eou-foundry --skill audit-judgment
Clone the repo
git clone --depth 1 https://github.com/xiaolai/eou-foundry

Made for: Claude Code.

Or install eou-foundry, the plugin that ships this one along with the rest of its 14 skills, 1 command.

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 audit-judgment

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaolai/eou-foundry/audit-judgment.svg)](https://agentmods.dev/skills/xiaolai/eou-foundry/audit-judgment)
Your own site
<a href="https://agentmods.dev/skills/xiaolai/eou-foundry/audit-judgment"><img src="https://agentmods.dev/badge/skills/xiaolai/eou-foundry/audit-judgment.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,157 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 5.1 $0.00089 $0.02157
Opus 5 $0.00044 $0.01078
Sonnet 5 $0.00018 $0.00431
Haiku 4.5 $0.00009 $0.00216

Measured 6d ago against content hash 5bde1a67667c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-judgment 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 6d 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.

codex/skills/audit-judgment/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Judgment

Audit the value_invocations of $target — an EOU with classification.judgment_authorized:true — against Rule 97 and the F14–F17 failure taxonomy.

What this skill does

Performs the fourth audit layer per D4.1 (post-ECP-0019). Audits agentic-judgment correctness, not output validity (that's $eou-validate), run correctness (run-trace validation), or EOU design (that's $eou-audit). The four layers compose; this skill is the agentic-judgment specialist.

Inputs

  • $target (required) — EOU ID resolved to foundry/eous/{id}.yml or foundry/meta-eous/{id}.yml, or a direct file path. Must have classification.judgment_authorized:true.
  • Auto-discovered: foundry/captured-workflows/cw-*.yml (the app's constitution); foundry/runs/{target}/ (run traces); optionally foundry/audits/eou-audits/{target}.audit.yml (prior $eou-audit findings).

Required reading

  1. target_eou_spec (the EOU under audit)
  2. foundry/captured-workflows/ (find the approved captured_workflow for the app)
  3. rules/97-value-invocation.md
  4. engine/failure-taxonomy.yml (F14–F17 definitions)
  5. engine/maturity-model.yml (judgment_maturity J0–J4 axis)
  6. schemas/run-trace.schema.yml (value_invocations entry shape)
  7. engine/meta-eous/audit-judgment.yml

Stop conditions

Halt and report without running checks if:

  • Target EOU has judgment_authorized:false or absent — Rule 97 does not apply.
  • No captured_workflow with complete human_approval exists for the app — judgment_authorized:true would itself be a validator failure per ECP-0018.
  • Target EOU is at lifecycle_stage: candidate or draft — Rule 97 enforcement begins at simulated per the exemption clause.
  • No run traces exist under foundry/runs/{target}/ — judgment_maturity is J0 or J1; nothing to audit yet. Emit "judgment_maturity:J1_INVOCATION_NAIVE — no runs to audit" status.

Procedure

Step 1 — Load and verify preconditions

Load target_eou_spec. Verify judgment_authorized:true. If false → "rule does not apply"; return.

Read the full file on GitHub · 132 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. 6d ago First seen · 132 lines · 89 tokens per session scan A 5bde1a67667c

Subscribe to this mod's changes

audit-judgment is a skill published in the GitHub repository xiaolai/eou-foundry (10 stars, last pushed 12d ago), licensed ISC. It adds 89 tokens to every session and 2,157 once invoked, about $0.0004 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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens