Borrowing it
Nothing to install: this file belongs to architect-34/triage-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/architect-34/triage-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/architect-34/triage-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/architect-34/triage-mcp/claude-md)<a href="https://agentmods.dev/instructions/architect-34/triage-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/architect-34/triage-mcp/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 5.1 | $0.01927 | $0.01927 |
| Opus 5 | $0.00963 | $0.00963 |
| Sonnet 5 | $0.00385 | $0.00385 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
triage-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 7d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
triage-mcp
Purpose
An issue-triage MCP server. Given a repository's historical GitHub issues, it helps answer triage questions — "has this been reported before?", "what labels does this belong under?", "who else hit this?" — by exposing retrieval-backed tools over MCP.
The pipeline is four stages, in order:
- ingest — harvest historical issues from the GitHub REST API into a
validated local dataset (
triage_mcp/ingest.py). - embed — encode issues into vectors and persist a searchable index
(
triage_mcp/store.py). - evaluate — measure retrieval quality against a labelled set and write the
numbers to disk (
triage_mcp/evals.py). - serve — expose the triage tools to MCP clients (
triage_mcp/server.py).
Local-first by design: no Docker, no database server. State lives in data/
(Parquet + JSONL) and results/ (metrics), both git-ignored.
Conventions
Type hints everywhere. Every function signature is annotated, including
tests. ruff enforces this (ANN rules) — run make lint.
Pydantic for structured data. Anything crossing a boundary — API responses, records written to disk, tool inputs and outputs — is defined as a pydantic model and validated. Do not pass bare dicts between modules.
Unit tests never touch the network. Tests run against checked-in fixtures in
tests/fixtures/. tests/conftest.py installs an autouse fixture that blocks
socket connections and httpx sends, so a test that reaches for the network
fails loudly instead of silently depending on GitHub being up and a token being
present.
Metrics are computed, never asserted. All metrics come from evals.py and
are written to results/<timestamp>/metrics.json. Never hardcode, estimate,
round from memory, or carry a number forward from a previous run — not in code,
not in docs, not in a chat reply. If a number has not been produced by an eval
run, the honest answer is that it is not known yet. When quoting a metric,
quote it from the metrics.json that produced it.
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.
- 7d ago First seen · 159 lines · 1,927 tokens per session scan A 968d1fb40fb3
triage-mcp CLAUDE.md is an instructions file published in the GitHub repository architect-34/triage-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,927 tokens to every session, about $0.0096 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.
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.