drift-audit

drift-audit is a skill for Claude Code, Codex from darrencroton/ai-agent-coder. It costs 52 tokens per session (864 once invoked), scanned A, original, MIT.

A scope-checking add-on that compares an implementation with an approved plan or contract before a normal code review.

In plain words
What is it for?
Use it to audit whether a completed change stayed within its allowed files, functions, components, stated non-goals, and expected validation. If no frozen contract exists, it reports that the audit is blocked.
Why use it?
It identifies work that was changed without authorization, while keeping code quality questions separate from scope questions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to audit whether a completed change stayed within its allowed…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/darrencroton/ai-agent-coder/drift-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 darrencroton/ai-agent-coder --skill drift-audit
Clone the repo
git clone --depth 1 https://github.com/darrencroton/ai-agent-coder

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 drift-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/darrencroton/ai-agent-coder/drift-audit.svg)](https://agentmods.dev/skills/darrencroton/ai-agent-coder/drift-audit)
Your own site
<a href="https://agentmods.dev/skills/darrencroton/ai-agent-coder/drift-audit"><img src="https://agentmods.dev/badge/skills/darrencroton/ai-agent-coder/drift-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 864 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 $0.00052 $0.00864
Opus 5 $0.00026 $0.00432
Sonnet 5 $0.00010 $0.00173
Haiku 4.5 $0.00005 $0.00086

Measured 6d ago against content hash 298757d1927c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

drift-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 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.

skills/drift-audit/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Audit

Use this skill to answer one question: was the implementation authorized?

This is not a general code review. Do not spend the review budget judging whether the code is elegant, optimal, or fully maintainable except where that proves scope drift. Quality review belongs to code-review after this gate passes.

Required Inputs

Identify or reconstruct these inputs before auditing:

  • frozen contract or slice receipt
  • allowed files/functions/components
  • explicit non-goals
  • expected tests or validation
  • actual diff, commit, branch, or changed files
  • relevant tests touched or expected

If no frozen contract exists, stop after drafting a candidate contract from the user request and mark the audit BLOCKED: no frozen contract. Do not pretend an inferred contract has the same authority as an approved one.

Never browse .pm/, .orchestrator/, archive/ (bookkeeping/log/archive, not content) — reading a specific path already named there is fine.

Workflow

  1. Read the frozen contract and list the authorized surface.
  2. Inspect the actual change set with git diff, git show, or the supplied patch.
  3. Compare actual changed files/functions/components against the authorized surface.
  4. Identify behaviour added, behaviour removed, hidden rewrites, missing tests, and new coupling.
  5. Check whether explicit non-goals were preserved.
  6. Return an authorization verdict before any quality judgement.

What Counts As Drift

Report drift when the implementation includes:

  • files, functions, components, schemas, routes, or configs outside the authorized surface
  • behaviour not listed in the acceptance criteria
  • removed or weakened edge cases
  • broad rewrites hidden inside a narrow task
  • new coupling to auth, billing, persistence, global state, routing, shared types, or API contracts
  • test changes that broaden, weaken, or silently redefine the requested behaviour
  • missing tests that were required by the frozen contract

Do not report drift for incidental formatting or import ordering unless it changes behaviour, coupling, public surface, or reviewability.

Read the full file on GitHub · 104 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 · 104 lines · 52 tokens per session scan A 298757d1927c

Subscribe to this mod's changes

drift-audit is a skill published in the GitHub repository darrencroton/ai-agent-coder (2 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 864 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.