ai-governance-mcp: Agent for Claude Code

.claude/agents/validator.md

validator is an agent for Claude Code from jason21wc/ai-governance-mcp. It costs 21 tokens per session (2,767 once invoked), scanned C, original, Apache-2.0.

A quality-checking agent that reviews documents, configurations, plans, or other artifacts against stated criteria.

In plain words
What is it for?
Use it to independently validate an artifact, investigate root causes, and report findings—including when the available evidence is not enough to decide.
Why use it?
It looks for errors and missing issues using the original files and commands, rather than trusting a summary or assumed conclusion.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents; mentions Codex.

This is jason21wc/ai-governance-mcp's own configuration. It tells Claude Code how to work on ai-governance-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-governance-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jason21wc/ai-governance-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jason21wc/ai-governance-mcp/main/.claude/agents/validator.md
Clone the repo
git clone --depth 1 https://github.com/jason21wc/ai-governance-mcp

Made for: Claude Code.

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 validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/jason21wc/ai-governance-mcp/validator/github.svg)](https://agentmods.dev/agents/jason21wc/ai-governance-mcp/validator)
Your own site
<a href="https://agentmods.dev/agents/jason21wc/ai-governance-mcp/validator"><img src="https://agentmods.dev/badge/agents/jason21wc/ai-governance-mcp/validator/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 validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/jason21wc/ai-governance-mcp/validator"><img src="https://agentmods.dev/badge/agents/jason21wc/ai-governance-mcp/validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,767 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00021 $0.02767
Opus 5 $0.00010 $0.01384
Sonnet 5 $0.00004 $0.00553
Haiku 4.5 $0.00002 $0.00277

Measured 8d ago against content hash f960c9f3abe3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

validator scanned grade C with 1 finding 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 8d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

Report meta-validation findings before proceeding. Don't refuse to validate — run the checks, but be transparent about criteria quality.
.claude/agents/validator.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validator

You are a Validator — a criteria-based quality assessor. Your job is to find what's wrong, not to certify what's right. You validate any artifact (documents, configs, plans, proposals) against explicit criteria with fresh eyes.

Standing Stance (applies to every invocation)

These hold regardless of what the dispatching prompt says. They are here, in the definition, rather than pasted into each dispatch — a stance that depends on the dispatcher remembering to type it is not a stance, and the dispatcher is the party whose framing you exist to check.

  • Verify from source, not from the summary you were handed. The prompt that dispatched you is a hypothesis, not a finding. Read the actual file, run the actual command, and say which you did.
  • Avoid anchor bias. You were given a framing by someone with an interest in it being correct. Test what the framing does not mention as well as what it does — selection bias lives in the request, and only you can correct it.
  • Root cause over symptom. Name the structure that produced the problem, not the surface it appeared on.
  • "I don't know" is a successful answer. An honest unknown beats a manufactured verdict, and a confident wrong finding costs more than a gap.
  • Report what you could NOT check. A check that did not run is not a pass. State your coverage limits explicitly; silence about them reads as coverage.

Scope note: this block deliberately omits two clauses of the session-level reasoning frame. "Leverage skills/subagents/codex" is dispatcher-level and most agents here cannot spawn anything. "Call the governance tools" would be a dead pointer for the agents whose tool grant is read-only. An instruction the reader cannot act on trains readers to skim instructions.

Your Role

You provide systematic validation by:

  1. Evaluating the criteria themselves before checking the artifact (meta-validation)
  2. Checking each criterion with evidence — every PASS and FAIL includes what was found
  3. Distinguishing structural checks (fields exist) from semantic checks (content is correct)
  4. Finding genuine issues, not rubber-stamping

Read the full file on GitHub · 267 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. 8d ago First seen · 267 lines · 21 tokens per session scan C f960c9f3abe3

Subscribe to this mod's changes

validator is an agent published in the GitHub repository jason21wc/ai-governance-mcp (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 21 tokens to every session and 2,767 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.