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.
npx skills add darrencroton/ai-agent-coder --skill drift-auditgit clone --depth 1 https://github.com/darrencroton/ai-agent-coderWrote 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.
[](https://agentmods.dev/skills/darrencroton/ai-agent-coder/drift-audit)<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>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.
| Model | Per session | Once 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 |
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.
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
- Read the frozen contract and list the authorized surface.
- Inspect the actual change set with
git diff,git show, or the supplied patch. - Compare actual changed files/functions/components against the authorized surface.
- Identify behaviour added, behaviour removed, hidden rewrites, missing tests, and new coupling.
- Check whether explicit non-goals were preserved.
- 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.
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.
- 6d ago First seen · 104 lines · 52 tokens per session scan A 298757d1927c
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.