Borrowing it
Nothing to install: this file belongs to hyang0129/pyscope-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.
curl -O https://raw.githubusercontent.com/hyang0129/pyscope-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/hyang0129/pyscope-mcpWrote 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/hyang0129/pyscope-mcp/claude-md)<a href="https://agentmods.dev/instructions/hyang0129/pyscope-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hyang0129/pyscope-mcp/claude-md/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.
<a href="https://agentmods.dev/instructions/hyang0129/pyscope-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hyang0129/pyscope-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01959 | $0.01959 |
| Opus 5 | $0.00979 | $0.00979 |
| Sonnet 5 | $0.00392 | $0.00392 |
| Haiku 4.5 | $0.00196 | $0.00196 |
Grade A, and why
pyscope-mcp 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 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.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pyscope-mcp — Claude instructions
What this repo is
A standalone pip-installable MCP server. Exposes function- and module-level call graphs of a target Python repo as MCP tools so agentic coding clients can query structure instead of grepping.
Package name on PyPI: pyscope-mcp. Import path: pyscope_mcp. Console script: pyscope-mcp.
Governing document — read before non-trivial changes
CONSTITUTION.md defines the non-negotiables this project is checked against. Any PR that adds features, changes the graph surface, or touches the serve/build split must keep all four laws and pass the Review Heuristic at the bottom of that file. In one-line summary:
- Never mislead the consumer — no uncertain edges, no silent truncation.
- Minimal startup; the serve path stays thin.
- Git-in-sync graph is the zero-friction default; drift is cheaply detectable.
- Graph update ≤60 s on standard PRs.
When the conventions below appear to conflict with the constitution, the constitution wins. If that happens, flag it — the convention is out of date.
Current status
The query layer, index format, CLI, MCP server, tests, and analyzer are all fully implemented and in production. The AST-based analyzer (build_raw and build_with_report) walks the target repo, resolves intra-package call edges, captures file-level SHA digests and skeleton symbols, and writes a versioned JSON index. Running pyscope-mcp build produces the index; pyscope-mcp serve loads it and answers MCP queries.
See docs/prior-art.md for the full pivot rationale (why we dropped pycg), the inherent limits of static analysis on dynamic Python, and a survey of how other code-graph MCPs solve these problems. The conventions below are the distilled takeaways — read prior-art.md for the reasoning.
The one contract the analyzer must satisfy
def build_raw(root: Path, package: str) -> dict[str, list[str]]: ...
- Keys: fully-qualified caller names, e.g.
my_pkg.module.functionormy_pkg.module.Class.method. - Values: lists of fully-qualified callees in the same form.
- Python 3.11+ native. No monkey-patching the import system. AST-based, not import-based.
- Per-file error isolation. A parse failure on one file must not abort the run — skip, warn, continue.
- No runtime import of target code. pycg's fatal mistake; don't repeat it.
- Deterministic output. Same repo in, same JSON out.
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.
- 8d ago First seen · 135 lines · 1,959 tokens per session scan A 636b90eb1395
pyscope-mcp CLAUDE.md is an instructions file published in the GitHub repository hyang0129/pyscope-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,959 tokens to every session, about $0.0098 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.