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 instructions/probelabs/visor/claude-mdgit clone --depth 1 https://github.com/probelabs/visorWhat 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 | $0.01903 | $0.01903 |
| Opus 5 | $0.00951 | $0.00951 |
| Sonnet 5 | $0.00381 | $0.00381 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
visor CLAUDE.md 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Visor is an AI-powered code review tool for GitHub Pull Requests that can run as both a GitHub Action and CLI tool. The project analyzes code for security, performance, style, and architectural issues using various AI providers (Google Gemini, Anthropic Claude, OpenAI GPT) and provides intelligent feedback.
Development Commands
Build and Development
npm run build- Build TypeScript to dist/npm run clean- Remove dist/ directorynpm run prebuild- Runs clean before build
Testing
npm test- Run all Jest tests (timeout: 10 minutes per user config)npm run test:watch- Run tests in watch modenpm run test:coverage- Generate coverage report
Code Quality
npm run lint- Lint TypeScript files in src/ and tests/npm run lint:fix- Auto-fix linting issuesnpm run format- Format code with Prettiernpm run format:check- Check code formatting
Running the Tool
./dist/cli-main.js --help- Show CLI help after building./dist/cli-main.js --check all- Run all checks./dist/cli-main.js --check security --output json- Security check with JSON output./dist/cli-main.js config snapshots- List config snapshots./dist/cli-main.js --slack --config .visor.yaml --watch- Slack mode with live config reload
Deployment
npm run deploy:site- Deploy site to Cloudflare Pagesnpm run deploy:worker- Deploy worker to Cloudflarenpm run deploy- Deploy both site and worker
Architecture Overview
Core Components
Entry Points:
src/index.ts- GitHub Action entry point, handles GitHub event processingsrc/cli-main.ts- CLI tool entry point, parses arguments and runs checks
Key Services:
src/reviewer.ts- Core review logic and issue scoring calculationssrc/ai-review-service.ts- AI provider abstraction for code analysissrc/pr-analyzer.ts- GitHub PR data extraction and diff processingsrc/pr-detector.ts- Detects PR context from various GitHub eventssrc/github-comments.ts- Manages GitHub PR comments and updatessrc/check-execution-engine.ts- Orchestrates running multiple check providers
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 · 171 lines · 1,903 tokens per session scan A bf195c9b5c83
visor CLAUDE.md is an instructions file published in the GitHub repository probelabs/visor (23 stars, last pushed 2d ago), licensed MIT. It adds 1,903 tokens to every session, about $0.0095 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 2026-08-30.
Other instructions, from other repositories
otter AGENTS.md
Instructions for AmadeusITGroup/otter, covering agents.md, quick start, context files, always relevant and task-specific context.
otter CLAUDE.md
Instructions for AmadeusITGroup/otter, a project described as: The Otter project is a highly modular framework whose goal is to provide a common platform to accelerate and facilitate the development of runtime customizable Angular based Web Applications.
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
movi-player AGENTS.md
Instructions for MrUjjwalG/movi-player, covering agents.md — movi-player for ai coding assistants, 1. what this is, 2. package entry points, 3. architecture map and 4. the web component .
sofagent GEMINI.md
Instructions for KongFangXun/sofagent, covering gemini.md · sofagent gemini cli 适配(薄挂载), 会话开始时按序加载(四层加载链), 审计强制(平台无关) and 连接 mcp server.