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 jason21wc/ai-governance-mcp --skill source-reviewgit clone --depth 1 https://github.com/jason21wc/ai-governance-mcpWrote 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/jason21wc/ai-governance-mcp/source-review)<a href="https://agentmods.dev/skills/jason21wc/ai-governance-mcp/source-review"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/source-review/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/jason21wc/ai-governance-mcp/source-review"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/source-review.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 | $0.00155 | $0.01263 |
| Opus 5 | $0.00077 | $0.00632 |
| Sonnet 5 | $0.00031 | $0.00253 |
| Haiku 4.5 | $0.00015 | $0.00126 |
Grade A, and why
source-review 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 10d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Context
After the skill loads, establish the project root and branch with ordinary
read-only calls. INFLUENCES.md at the repo root is the attribution SSOT;
verdicts are proposed for it and applied with any influenced method.
Instructions
You are reviewing an external source against ai-governance. The discriminating move is intent-abstraction: a surface item (a named principle/method/tool) can look novel while its intent is already covered, or look familiar while its intent is genuinely new. Intent is the unit of comparison. Read procedure.md in this skill folder for the full 6-phase protocol; this is the orchestration shell.
This skill proposes, it does not write — it has no Edit/Write tool. It returns a verdict report; the human applies the approved rows/items (per the INFLUENCES.md same-commit discipline).
Quick Start
-
Collect the Runtime Context above and acquire the source. Accept whichever the user provides: pasted text, a local file path (
Read), a URL (WebFetch), or a topic to find first (WebSearch→WebFetch). If ambiguous, ask. For a long, local, or multi-page source, filter before you read: save or pipe the raw text and runpython scripts/semantic_rank.py --raw --query "<review question>" --stats < source.md, then read only the top-ranked passages — do NOT ingest the full source into context first (the semantic filter runs before the content reaches you). -
Read
procedure.mdfor the full protocol, then run all six phases in order:- (0) Govern —
evaluate_governance(planned_action="review external source against governance"). - (1) Ingest — load the source text.
- (2) Extract (face value) — enumerate the discrete items (principles / methods / tools / claims); state "N items identified" (per rules-of-procedure §9.8.5 enumeration-verification).
- (3) Abstract-to-intent — for each item write the intent: the failure-mode/goal above the surface (per
meta-core-systemic-thinking+ Intent Discovery). This is the crux. - (4) Coverage-check the intent —
query_governance+search_references+query_projectfor each intent; apply the §9.8.2 Duplication Check. - (5) Classify + gate the "new" — map each intent to one of the four INFLUENCES categories or "genuinely new." For every "genuinely new" candidate, run the §9.8.1 Admission Test (7 Qs) and dispatch a
contrarian-reviewerpass to guard against intellectual-generosity bias (LEARNING-LOG 2026-02-28). - (6) Propose — emit the verdict report; route each verdict per INFLUENCES.md "How to extend." Do not write.
- (0) Govern —
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.
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.
- 10d ago First seen · 47 lines · 155 tokens per session scan A ce8dc3134f1d
source-review is a skill published in the GitHub repository jason21wc/ai-governance-mcp (0 stars, last pushed 10d ago), licensed Apache-2.0. It adds 155 tokens to every session and 1,263 once invoked, about $0.0008 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…