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/corbym/backlog-mcp/claude-mdgit clone --depth 1 https://github.com/corbym/backlog-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/corbym/backlog-mcp/claude-md)<a href="https://agentmods.dev/instructions/corbym/backlog-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/corbym/backlog-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 | $0.01528 | $0.01528 |
| Opus 5 | $0.00764 | $0.00764 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
backlog-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 4d 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.
backlog-mcp: Project Context for Claude Code
What this is
A local MCP server written in Go that gives AI agents shared read/write access to a story-based project backlog. The server exposes nine tools that let agents create epics and stories, list and read story content, set acceptance criteria, update status, append notes, and complete stories — all backed by plain markdown files on disk.
The filesystem is always the source of truth. The MCP server is a convenience layer on top, never a replacement.
The story file structure
requirements-index.md # master index, source of truth for status/title
backlog.md # priority-ordered list of not-done stories
epic-NNN-slug/
epic-NNN.md
story-NNN.md
Story IDs: STORY-NNN (e.g. STORY-047)
Epic IDs: EPIC-NNN (e.g. EPIC-003)
File path pattern: epic-003-enemy-system/story-009.md
Status values: draft, in-progress, done, blocked
Status is tracked in requirements-index.md (table column) and backlog.md (inline marker like *(in-progress)*). Status is NOT in the story files themselves.
Backlog rules:
- When a story reaches
done, remove it from the backlog and renumber - Priority order is head-of-list first
- Never insert in the middle — new stories append to the end
Repository layout
backlog/
main.go # entry point: init / plan subcommands, stdio server
init.go # scaffold a new backlog directory
plan.go # scaffold a new plan file
server.go # MCP server construction, stdio runner
tools.go # all 9 tool handlers
config.go # config loading, defaults to ./requirements
parser/
index.go # parse + mutate requirements-index.md
backlog.go # parse + mutate backlog.md
story.go # filesystem scan, read story files, append notes
atomic.go # shared atomic write helper (temp file + rename)
go.mod
README.md
Environment variables
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.
- 4d ago First seen · 159 lines · 1,528 tokens per session scan A 1b2054d4b063
backlog-mcp CLAUDE.md is an instructions file published in the GitHub repository corbym/backlog-mcp (3 stars, last pushed 1mo ago), licensed Unlicense. It adds 1,528 tokens to every session, about $0.0076 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
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
tmetric-minimal-mcp CLAUDE.md
Claude Code instructions for guglielmo/tmetric-minimal-mcp, covering claude.md, development commands, project architecture, file structure and core architecture patterns.
shelly-forge CLAUDE.md
Claude Code instructions for mslavov/shelly-forge, covering documentation usage guidelines, critical: framework-first reading order, 📚 mandatory reading order, pre-task protocol and post-task protocol.
vibelive AGENTS.md
AGENTS.md instructions for pooriaarab/vibelive, covering agents.md, repository context, pull requests, cloud agents (cursor) and install & test.
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).