audit-loop-scaffold

audit-loop-scaffold is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 75 tokens per session (1,210 once invoked), scanned A, a copy of audit-loop-scaffold, Apache-2.0.

A repair tool for four files that define an audit loop: its state, checks, budget, and run log. It compares them with fixed templates, backs up existing content, restores failed changes, and reports other drift.

In plain words
What is it for?
Use it when an audit-loop directory no longer matches its approved templates. It repairs STATE.md, gate.yaml, loop-budget.md, and loop-run-log.md, while identifying drift elsewhere.
Why use it?
It helps keep repeated audit runs consistent when scaffold files have been edited or become out of sync. Only the named scaffold files are automatically rewritten.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the odin-agent plugin — 46 skills shipped together

Good fit Use it when an audit-loop directory no longer matches its approved templates. It repairs STATE.md, gate.yaml, loop-budget.md, and loop-run-log.md, while identifying drift elsewhere.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/audit-loop-scaffold
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 OutlineDriven/odin-claude-plugin --skill audit-loop-scaffold
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-agent, the plugin that ships this one along with the rest of its 46 skills.

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-loop-scaffold

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/audit-loop-scaffold.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/audit-loop-scaffold)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/audit-loop-scaffold"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/audit-loop-scaffold.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,210 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 100% copy Near-identical to another mod 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 $0.00075 $0.01210
Opus 5 $0.00037 $0.00605
Sonnet 5 $0.00015 $0.00242
Haiku 4.5 $0.00007 $0.00121

Measured 4d ago against content hash c927acaa1677, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-loop-scaffold 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 4d 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.

Origin

This is a copy

100% identical to audit-loop-scaffold — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/odin-agent/skills/audit-loop-scaffold/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit loop scaffold

Contract

Field Bound contract
Trigger Loop scaffold files have drifted from their templates or from each other
Authority Write only the four named auto-fixable files; retain pre-write content (including the absence state for newly created files) to enable rollback; roll back on verification failure
Side effect Rewrites only STATE.md, gate.yaml, loop-budget.md, loop-run-log.md from templates; reports every other drifted file
Done Scaffold files match their templates or drift is reported with its exact file; nothing outside the fixed set was written

Inputs

Input Required Description
loop_dir yes path to the loop directory containing scaffold files
templates yes STATE.md.template, gate.yaml.template, loop-budget.md.template, loop-run-log.md.template from the loop-engineering provenance

Templates must be sourced from cobusgreyling/loop-engineering at revision d03dcb92. No other skill, module, AGENTS file, or planning artifact is required.

Procedure

  1. Resolve loop_dir to an absolute path. Fail with loop_dir_unavailable if it does not exist or is not a directory. Done when: loop_dir resolves to an existing directory.
  2. Read the four template files into memory. Fail with template_unavailable if any template cannot be read. Done when: all four templates are in memory.
  3. List every file in loop_dir at depth 1 (direct children only). Done when: the direct-child file list is complete.
  4. Back up pre-write state for the four auto-fixable files. For each name (STATE.md, gate.yaml, loop-budget.md, loop-run-log.md): if the target file exists, record its content and hash; if it does not exist, record its absence. This backup is the rollback source. Done when: pre-write state for all four auto-fixable files is recorded, including absence states.
  5. Converge the four files to template content. For each auto-fixable name: a. Compute the target path as loop_dir/<name>. b. If the target does not exist or its hash differs from the template hash, write the template content to the target path. c. Record the write in the action log with before/after hashes (before hash is null for newly created files). Done when: every auto-fixable file matches its template or is written from it, and before/after hashes are recorded.
  6. For every other file in loop_dir not in the auto-fixable set: compute the file hash. If the hash matches none of the four template hashes, record the file path and hash in the drift report. Done when: every non-auto-fixable drifted file is in the drift report.
  7. Verify every written auto-fixable file matches its template byte-for-byte by re-reading and comparing hashes. If any verification fails, roll back every file written in step 5 to its pre-write content from the step 4 backup: restore existing files to their recorded content, and delete files that were newly created (whose pre-write state was absence). Fail with auto_fix_verify_failed. Done when: every written file matches its template byte-for-byte.
  8. Assert: every auto-fixable file matches its template; every other drifted file is in the drift report. If the assertion fails, fail with non_converged. Done when: the assertion holds.
  9. Return the complete drift report. Done when: the drift report is returned.

Read the full file on GitHub · 84 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. 4d ago First seen · 84 lines · 75 tokens per session scan A c927acaa1677

Subscribe to this mod's changes

audit-loop-scaffold is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 1,210 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to audit-loop-scaffold, differing in 4 lines, and is treated as a copy.

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-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

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