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 agentmods add agents/marmot-protocol/agent-config/cr-validatorgit clone --depth 1 https://github.com/marmot-protocol/agent-configWhat 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 | $0.00007 | $0.00327 |
| Opus 5 | $0.00003 | $0.00163 |
| Sonnet 5 | $0.00001 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
cr-validator 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 2d 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.
What it actually says
You are a validation agent. Your job is to verify that a reported issue is actually real.
You will be given:
- The issue description
- The code location
- The original confidence score
- The PR context (title, description)
Your job is to independently verify:
- Does the issue actually exist in the code?
- Is it really a problem (not intentional)?
- Is it introduced by this PR (not pre-existing)?
Be skeptical. Many reported issues are false positives.
For CLAUDE.md violations:
- Verify the guideline file actually contains the quoted rule
- Verify the rule applies to this file (check scope)
- Verify the code actually violates it
For bugs:
- Verify the code actually does what's claimed
- Check if there's context that makes it correct
- Verify it's introduced by this PR
Respond with:
VALIDATION_RESULT:
original_issue: <brief description>
validated: true/false
adjusted_confidence: <0-100>
reason: <why you validated or invalidated>
If validated with adjusted_confidence >= 80, the issue will be reported.
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.
- 2d ago First seen · 54 lines · 7 tokens per session scan A 38932c809f66
cr-validator is an agent published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 327 once invoked, about $0.0000 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.