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/cuongph-dev-work/backlog_mcp/claude-mdgit clone --depth 1 https://github.com/cuongph-dev-work/backlog_mcpWhat 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 | $0.03037 | $0.03037 |
| Opus 5 | $0.01519 | $0.01519 |
| Sonnet 5 | $0.00607 | $0.00607 |
| Haiku 4.5 | $0.00304 | $0.00304 |
Grade A, and why
backlog_mcp CLAUDE.md scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **HTTP via `BacklogHttpClient`.** All Backlog REST API calls go through `src/backlog/http-client.ts` (Axios). API Key auto-appended via `axios.create({ params: { apiKey } })`. This is a copy
72% identical to claude-code-trace AGENTS.md — 228 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Instructions for Claude Code
Read this file in full before working on this project. This is the canonical instruction set for Claude when working on
backlog-mcp.
Project Overview
backlog-mcp is a TypeScript MCP (Model Context Protocol) server providing AI agents with read access to a Backlog (Nulab) space. Authentication uses a static API Key in .env — no browser or OAuth required.
Stack: TypeScript (strict, ESM/NodeNext), Express, @modelcontextprotocol/sdk, Axios, Zod, Vitest.
Architecture Rules
- Factory pattern per request. Each MCP request creates a new
McpServer+StreamableHTTPServerTransport. Never reuse across requests. - Auth is a config concern.
BacklogHttpClientreceivesapiKeyfromconfigat construction. Tool handlers never handle auth directly. - HTTP via
BacklogHttpClient. All Backlog REST API calls go throughsrc/backlog/http-client.ts(Axios). API Key auto-appended viaaxios.create({ params: { apiKey } }). - Zod validates everything. Env vars (
src/config.ts) and tool inputs (schema in each tool file) are Zod-validated before use. - Two-layer type system.
src/types/backlog-api.ts— raw Backlog REST response shapes (used only inhttp-client.tsandmappers.ts)src/types.ts— normalized domain interfaces (used everywhere else)src/backlog/mappers.ts— bridges raw → domain
Coding Standards
- No
any. TypeScript strict mode. All types must be explicit. - ESM
.jsextensions. Every import:import "./foo.js"not"./foo". McpErrorfor all errors. Use factory helpers fromsrc/errors.ts. Neverthrow new Error(...)for business logic.isError: trueon error responses. MCP clients depend on this flag — never return errors as normal content.- 401/403 = invalid API key.
assertOk()in the HTTP client handles this; tool handlers justcatch (McpError). - Shared helpers →
src/utils.ts. Date formatting, string manipulation, etc. go there — not inline in handlers. - Prefer npm packages over hand-rolled code. Use established libraries for common tasks.
- Raw types stay in
backlog-api.ts. Never leak raw Backlog API shapes into tool handlers.
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 · 231 lines · 3,037 tokens per session scan A 1b72c41dba19
backlog_mcp CLAUDE.md is an instructions file published in the GitHub repository cuongph-dev-work/backlog_mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 3,037 tokens to every session, about $0.0152 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 72% identical to claude-code-trace AGENTS.md, differing in 228 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.