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/jmanhype/mcphoenix/claude-mdgit clone --depth 1 https://github.com/jmanhype/MCPhoenixWrote 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/instructions/jmanhype/mcphoenix/claude-md)<a href="https://agentmods.dev/instructions/jmanhype/mcphoenix/claude-md"><img src="https://agentmods.dev/badge/instructions/jmanhype/mcphoenix/claude-md.svg" alt="Measured on agentmods" 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 | $0.00525 | $0.00525 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
MCPhoenix 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 4d 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.
This is a copy
100% identical to vggt-mps CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Guardrails
This file defines what Claude Code is allowed to modify when performing automated improvements.
Allowed Modifications
Claude Code MAY modify:
- Documentation files (README.md, docs/*, *.md)
- Source code for:
- Bug fixes and error handling
- Code quality improvements (remove duplication, add type hints)
- Performance optimizations
- Refactoring for clarity/maintainability
- Security fixes
- Test files (add new tests, fix broken tests, improve coverage)
- CI/CD configurations (.github/workflows/*, .gitlab-ci.yml, etc.)
- Configuration files (build configs, linting rules, etc.)
- Metadata files (package.json, pyproject.toml, setup.py)
- GitHub-specific files (.gitignore, CODEOWNERS, etc.)
- Dependencies (with clear justification for updates/additions)
Restricted Modifications
Claude Code MUST NOT:
- Break public APIs or change function signatures without discussion
- Make breaking changes to existing behavior
- Change core algorithms without explaining rationale
- Remove features without justification
- Add heavy dependencies without clear need
- Modify production configuration (database URLs, API keys, etc.)
Exception: Issues Labeled ai-implement
When an issue is labeled ai-implement, Claude Code may modify source code to implement the requested feature or fix, but must:
- Reference the issue number in the PR
- Follow existing code style and patterns
- Include tests if the project has a test suite
- Not change public APIs without discussion in the issue
Pull Request Requirements
All PRs created by Claude Code MUST include:
- A clear description of what was changed and why
- A receipt line in the format:
Receipt: <hash> - Reference to the workflow run that created it
- Minimal, focused changes (prefer small PRs over large ones)
General Principles
- Minimal Deltas: Make the smallest change that solves the problem
- No Breaking Changes: Never introduce breaking changes
- Follow Existing Patterns: Match the style and structure of existing code
- Documentation First: When in doubt, improve documentation rather than code
- Safety First: If uncertain, create an issue for human review instead of making 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.
- 4d ago First seen · 59 lines · 525 tokens per session scan A b4f174ea9e5c
MCPhoenix CLAUDE.md is an instructions file published in the GitHub repository jmanhype/MCPhoenix (67 stars, last pushed 5mo ago), licensed MIT. It adds 525 tokens to every session, about $0.0026 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to vggt-mps CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.