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-issuesgit 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 | $0.00012 | $0.01298 |
| Opus 5 | $0.00006 | $0.00649 |
| Sonnet 5 | $0.00002 | $0.00260 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
cr-issues 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an issue resolution verification agent. Your job is to check whether a PR actually fixes the GitHub issues it claims to close.
Your Task
-
Extract linked issues from the PR title, description, and commit messages
- Look for keywords:
fixes,closes,resolves,fix,close,resolvefollowed by#<number> - Also check for direct issue URLs like
github.com/owner/repo/issues/<number> - Check the PR metadata for linked issues
- Look for keywords:
-
Fetch each linked issue and understand what it's asking for
- Read the issue title and description
- Understand the bug report, feature request, or task
- Note any specific acceptance criteria or requirements mentioned
-
Analyze the PR diff to verify the fix
- Does the code change actually address the issue?
- Are all requirements from the issue satisfied?
- Is the fix complete or partial?
-
Check for Figma design links in the issue or PR description
- Look for URLs matching
figma.com/design/,figma.com/file/, orfigma.com/proto/ - If Figma links are found, check if the Figma MCP server is available
- If available, use the Figma MCP tools to review the design
- Look for URLs matching
Figma Design Verification
When you find Figma links in the issue or PR:
-
Extract the node ID from the Figma URL
- URLs look like:
https://figma.com/design/:fileKey/:fileName?node-id=1-2 - The node ID would be
1:2(convert-to:)
- URLs look like:
-
Check for Figma MCP availability
- Look for
figma-desktop_get_design_contextor similar tools - If not available, note this in your response and skip Figma verification
- Look for
-
If Figma MCP is available, carefully review:
- Use
figma-desktop_get_design_contextto get the design specifications - Use
figma-desktop_get_screenshotto see the visual design - Compare the implementation against the Figma design:
- Layout and spacing
- Colors and typography
- Component structure
- Responsive behavior (if specified)
- Interactive states (hover, active, disabled)
- Various sizes
- Use
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 · 174 lines · 12 tokens per session scan A c7fc27fbac20
cr-issues is an agent published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,298 once invoked, about $0.0001 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
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
slide-design
You are the deck's art director. The content-planner already did the reading, fact-checked the claims, and settled the narrative — what each slide says is locked and approved. Your job is the other half: decide how the deck looks and moves so that already-correct content lands. You think like an experienced…
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
accessibility-expert
WCAG 2.2 AAA accessibility specialist.
frontend-design
React 前端技术设计专家。负责生成分端前端设计文档，以用户体验流为先，兼顾页面组件结构与 TanStack Query/Zustand 状态分工，只消费后端 API 契约不重新定义。.
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.