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/christopherdavenport/github-twin/claude-mdgit clone --depth 1 https://github.com/ChristopherDavenport/github-twinWhat 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 | $0.07884 | $0.07884 |
| Opus 5 | $0.03942 | $0.03942 |
| Sonnet 5 | $0.01577 | $0.01577 |
| Haiku 4.5 | $0.00788 | $0.00788 |
Grade C, and why
github-twin CLAUDE.md scanned grade C with 1 finding 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
`~/.config/gcloud/application_default_credentials.json` and never How it starts
The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project context for agentic readers (Claude Code, etc.). User-facing docs are
in README.md and getting_started.md.
What this is
A personal RAG over GitHub history exposed as an MCP server. Two target kinds, one DB per target:
- User mode — one person's commits + review comments. The original P1/P2 scope: "write like me" + "review like me".
- Org mode — a whole GitHub org's files-at-HEAD + commits + reviews across
all members. Adds an
author_loginaxis for filtering and per-reviewer evaluation.
Built phase by phase: P1 retrieval → P2 distillation → O-A through O-F
(target abstraction, repo discovery, file-at-HEAD ingest with
process-and-purge clones, org-wide commits + reviews, distill ergonomics,
scale polish) → P3 predict_review_outcome → held-out eval (gt eval).
Status
Stable. 283 tests + 7 skipped (the skips are optional sentence-transformers
and faiss deps). User-mode and org-mode are both functional end-to-end.
Retrieval is hybrid (BM25 + vector via RRF) by default. Code chunking is
AST-aware via tree-sitter for python / scala / javascript / typescript
(+ tsx) / go / rust, with a line-window fallback for unsupported
languages or parser failures. Embed text is prefixed with a deterministic
per-chunk header (path / symbol / node-kind / leading docstring) so vector
queries can hit chunks by NL even when the body contains only identifiers —
see src/github_twin/embed/prefix.py and EMBED_TEXT_VERSION in
pipeline.py. Bump the version constant whenever the prefix shape changes;
the next gt embed wipes vec_chunk and re-embeds.
~/.local/bin/uv run pytest -q # expect 363 passed + 7 skipped
~/.local/bin/uv run ruff check src/ tests/
~/.local/bin/uv run ruff format --check src/ tests/
~/.local/bin/uv run mypy # strict on src/github_twin/; tests not in scope
~/.local/bin/uv run gt stats # live user-mode DB sanity
~/.local/bin/uv run gt eval search evals/queries/default.yaml # retrieval dogfood
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 · 547 lines · 7,884 tokens per session scan C a4bbb2c44352
github-twin CLAUDE.md is an instructions file published in the GitHub repository ChristopherDavenport/github-twin (0 stars, last pushed 2mo ago), licensed MIT. It adds 7,884 tokens to every session, about $0.0394 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
github-mcp-server copilot-instructions.md
Copilot instructions for github/github-mcp-server, covering github mcp server - copilot instructions, project overview, critical build & validation steps, required commands (run before committing) and when modifying mcp tools/endpoints.
octocode AGENTS.md
Instructions for Muvon/octocode, covering octocode — ai-powered code intelligence, project structure, where to look, how things work and configuration — no defaults rule.
codesearch AGENTS.md
Instructions for flupkede/codesearch, covering agents.md — codesearch, current state, implemented features, open todos and ⚠️ branching & pr workflow (read first).
teamxray copilot-instructions.md
Instructions for AndreaGriffiths11/teamxray, covering github copilot instructions for mcp team x-ray extension, response style, build, test, and lint commands, validating extension changes and architecture.
teamxray AGENTS.md
Instructions for AndreaGriffiths11/teamxray, covering agents.md, purpose, tagline, tech stack and architecture.
mimirs CLAUDE.md
Claude Code instructions for TheWinci/mimirs, a project described as: Local MCP server that gives AI coding agents persistent, searchable memory of your codebase.