triage-mcp: Instructions file for Claude Code

CLAUDE.md

triage-mcp CLAUDE.md is an instructions file for Claude Code from architect-34/triage-mcp. It costs 1,927 tokens per session, scanned A, original, MIT.

A project instruction file for triage-mcp, an issue-triage server that searches historical GitHub issues. It documents the project's purpose, four-stage data pipeline, conventions, and commands.

In plain words
What is it for?
It guides work on importing GitHub issues, creating a searchable vector index, measuring retrieval quality, serving MCP tools, and following the project's validation and typing conventions.
Why use it?
It gives an agent the repository-specific rules needed to modify or operate the project consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is architect-34/triage-mcp's own configuration. It tells Claude Code how to work on triage-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything triage-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/architect-34/triage-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/architect-34/triage-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for triage-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/architect-34/triage-mcp/claude-md.svg)](https://agentmods.dev/instructions/architect-34/triage-mcp/claude-md)
Your own site
<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>
Per session 1,927 This file is loaded in full into every session.
When invoked 1,927 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 968d1fb40fb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

CLAUDE.md · 159 lines

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:

  1. ingest — harvest historical issues from the GitHub REST API into a validated local dataset (triage_mcp/ingest.py).
  2. embed — encode issues into vectors and persist a searchable index (triage_mcp/store.py).
  3. evaluate — measure retrieval quality against a labelled set and write the numbers to disk (triage_mcp/evals.py).
  4. 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.

Read the full file on GitHub · 159 lines

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.

  1. 7d ago First seen · 159 lines · 1,927 tokens per session scan A 968d1fb40fb3

Subscribe to this mod's changes

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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens