govern-update

govern-update is a skill for Claude Code, Codex from oakandfeather/ai-assisted-coding-governance. It costs 114 tokens per session (731 once invoked), scanned A, original, MIT.

An update procedure for an already-installed AI-assisted coding governance package. It refreshes the package’s shared rules and owned parts of its entry files while preserving project-specific settings.

In plain words
What is it for?
Updating the package from a supplied local path, environment variable, or upstream repository while leaving client-owned configuration untouched.
Why use it?
It keeps the installed governance rules current without replacing the repository’s own profiles, policies, or active client settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Updating the package from a supplied local path, environment variable, or upstream repository while leaving client-owned configuration untouched.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oakandfeather/ai-assisted-coding-governance/govern-update
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 oakandfeather/ai-assisted-coding-governance --skill govern-update
Clone the repo
git clone --depth 1 https://github.com/oakandfeather/ai-assisted-coding-governance

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 govern-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/oakandfeather/ai-assisted-coding-governance/govern-update/github.svg)](https://agentmods.dev/skills/oakandfeather/ai-assisted-coding-governance/govern-update)
Your own site
<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.

agentmods 80×15 button for govern-update

Your own site · 80×15
<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>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 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 $0.00114 $0.00731
Opus 5 $0.00057 $0.00365
Sonnet 5 $0.00023 $0.00146
Haiku 4.5 $0.00011 $0.00073

Measured 9d ago against content hash 8d9eb680e9fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

ai-docs/skills/govern-update/SKILL.md · 28 lines

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:

  1. A path the user gives you.
  2. $AI_GOVERNANCE_PATH if set.
  3. Clone it: git clone --depth 1 https://github.com/oakandfeather/ai-assisted-coding-governance into 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.
  4. 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.

Read the full file on GitHub · 28 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. 9d ago First seen · 28 lines · 114 tokens per session scan A 8d9eb680e9fe

Subscribe to this mod's changes

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.

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

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…

vercel/next.js · 83 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