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 oakandfeather/ai-assisted-coding-governance --skill govern-updategit clone --depth 1 https://github.com/oakandfeather/ai-assisted-coding-governanceWrote 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/oakandfeather/ai-assisted-coding-governance/govern-update)<a href="https://agentmods.dev/skills/oakandfeather/ai-assisted-coding-governance/govern-update"><img src="https://agentmods.dev/badge/skills/oakandfeather/ai-assisted-coding-governance/govern-update/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.
<a href="https://agentmods.dev/skills/oakandfeather/ai-assisted-coding-governance/govern-update"><img src="https://agentmods.dev/badge/skills/oakandfeather/ai-assisted-coding-governance/govern-update.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00114 | $0.00731 |
| Opus 5 | $0.00057 | $0.00365 |
| Sonnet 5 | $0.00023 | $0.00146 |
| Haiku 4.5 | $0.00011 | $0.00073 |
Grade A, and why
govern-update 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 9d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
govern-update
This file is a launcher, not the procedure. The procedure lives in the governance repo at ai-docs/procedures/govern-update.md, and is read fresh from there on every run — so it is current as of the source repo's last git pull, no matter how old this launcher is.
1. Locate the source package
Find the upstream package in this order:
- A path the user gives you.
$AI_GOVERNANCE_PATHif set.- Clone it:
git clone --depth 1 https://github.com/oakandfeather/ai-assisted-coding-governanceinto a temp directory. Use a temp directory, not a remote added to the target repo — the target's git state is the client's, and this must not touch it. - Ask. Do not reconstruct the rule files from memory — a paraphrased safety rule is not the safety rule. If you cannot find the source package, stop and say so.
No client overlay is needed here. govern-init has one — an optional private source of client profiles and policies — because it authors client material. This procedure never touches it: ai-governance/client-profiles/ and ai-governance/client-policies/ are tier E, left alone entirely. There is nothing for an overlay to supply.
2. Read the procedure and follow it
Read ai-docs/procedures/govern-update.md from the resolved source, and follow it exactly. It is the whole procedure — the staleness check on the source itself, the layouts to refuse, the anchors, the A–E tiers, the two merges, and the hand-off. Nothing in this launcher supersedes it.
If that file is not there, you are stale — stop. Either this launcher predates the source it is pointed at, or the source predates the split that created ai-docs/procedures/. Show the user what you found, and offer to re-deploy both skills (govern-init and govern-update) from ai-docs/skills/ into ~/.claude/skills/ before proceeding. Do not fall back to updating from memory.
That check matters more here than anywhere: a stale updater updates backwards — it will happily "restore" an obsolete file layout over a correct one. ~/.claude/skills/ is a one-shot copy that git pull does not touch, and it has already bitten this package: a deployed govern-init went unnoticed long enough to start scaffolding a pre-restructure shape (rule files at the repo root, a since-split ai-coding-rules.md) out of perfectly current rules. Keeping the procedure in the source repo is what turns that failure from silent into a hard stop — but only if you honor the stop.
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.
- 9d ago First seen · 28 lines · 114 tokens per session scan A 8d9eb680e9fe
govern-update is a skill published in the GitHub repository oakandfeather/ai-assisted-coding-governance (2 stars, last pushed 2d ago), licensed MIT. It adds 114 tokens to every session and 731 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…