Backlog.md-mcp CLAUDE.md

Backlog.md-mcp CLAUDE.md is an instructions file for coding agents from radleta/Backlog.md-mcp. It costs 521 tokens per session, scanned A, original, MIT.

Instructions for a server that lets AI agents manage Backlog.md projects; Backlog.md is a text-based way to track work items and their details.

In plain words
What is it for?
Use them when installing the server, changing its code, or creating and organizing Backlog.md work items.
Why use it?
They explain which documentation applies to users or contributors and how to structure tasks with criteria, dependencies, smaller tasks, and priorities.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/radleta/backlog.md-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/radleta/Backlog.md-mcp

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 Backlog.md-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/radleta/backlog.md-mcp/claude-md.svg)](https://agentmods.dev/instructions/radleta/backlog.md-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/radleta/backlog.md-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/radleta/backlog.md-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 521 This file is loaded in full into every session.
When invoked 521 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00521 $0.00521
Opus 5 $0.00260 $0.00260
Sonnet 5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured 5d ago against content hash 61893a8d733a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Backlog.md-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 5d 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 · 52 lines

What it actually says

Backlog.md MCP Server - Claude Instructions

Documentation Organization

@.github/README.md @README.md

Important: The documentation above is organized by audience:

  • .github/README.md - For developers contributing to the MCP server codebase (includes development setup, testing, and architecture)
  • README.md - For users installing and using the MCP server (displayed on npm package page)
  • CLAUDE.md (this section) - Claude-specific context and guidance

Claude-Specific Context

Understanding Your Audiences

When helping with this project, identify which audience you're serving:

  • Users want to install and use the MCP server with their Backlog.md projects
  • Developers want to contribute to or modify the MCP server codebase itself

Effective Task Management Guidance

When using the Backlog.md tools, always consider:

  1. Acceptance Criteria - Define measurable completion conditions
  2. Dependencies - Set execution order between related tasks
  3. Sub-tasks - Break complex work into manageable pieces
  4. Priority - Indicate task importance (high/medium/low)

Example workflow:

  • Create parent task for major feature
  • Add sub-tasks for implementation steps
  • Set dependencies between sub-tasks
  • Include acceptance criteria for each task
  • Use sequence_list to verify execution order

Implementation Notes

Some features are MCP enhancements beyond the native CLI:

  • Label filtering in task_list: O(n) calls - expensive for large task lists
  • Decision operations: Efficient - direct filesystem access
  • Resource aggregation: Multiple CLI calls with in-memory processing

Most operations are direct CLI pass-through for data integrity.

Key Points to Remember

  1. The MCP server is a wrapper around Backlog.md CLI - it doesn't implement custom write logic
  2. All security measures preserve user content (escape, don't remove)
  3. Interactive commands (like backlog init) cannot be implemented through MCP
  4. For Claude Code setup, users should use: claude mcp add backlog-md -- backlog-mcp start
  5. Development documentation is now in .github/README.md, user documentation is in README.md
  6. You can actively test the MCP server in your current session using backlog-mcp-dev mcp commands. If it doesn't exist, ask the user to install it via claude mcp add backlog-md-dev -- /path/to/local/repo/bin/backlog-mcp-dev.js start
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. 5d ago First seen · 52 lines · 521 tokens per session scan A 61893a8d733a

Subscribe to this mod's changes

Backlog.md-mcp CLAUDE.md is an instructions file published in the GitHub repository radleta/Backlog.md-mcp (5 stars, last pushed 9mo ago), licensed MIT. It adds 521 tokens to every session, about $0.0026 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

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

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

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 · 5,182 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

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.

deepseek-ai/deepseek-harness · 3,733 tokens