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/backloghq/backlog/claude-mdgit clone --depth 1 https://github.com/backloghq/backlogWhat 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 | $0.04036 | $0.04036 |
| Opus 5 | $0.02018 | $0.02018 |
| Sonnet 5 | $0.00807 | $0.00807 |
| Haiku 4.5 | $0.00404 | $0.00404 |
Grade A, and why
backlog 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 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.
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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
backlog — Task Management Plugin
Claude Code plugin and MCP server with a native TypeScript engine for persistent cross-session task management. No external dependencies beyond Node.js.
Purpose
Claude Code sessions are ephemeral — task context dies with the conversation. This MCP server bridges that gap by giving agents read/write access to a persistent task store, so tasks created in one session can be picked up in another. Agent teams can coordinate work through shared task state: assignments, annotations, projects, and dependencies.
Project Isolation
Isolation can be achieved at the directory level (separate data folders) or at the collection level (namespaces within the same folder).
- Directory Isolation (Primary):
- Plugin mode (
TASKDATA_ROOT): Auto-derives a project-specific subdirectory from the working directory. E.g.,TASKDATA_ROOT=/data/projects+ CWD/home/user/dev/my-app→/data/projects/my-app-a1b2c3d4/. The slug is<basename>-<md5(cwd)[0:8]>. - Standalone mode (
TASKDATA): Explicit path to task data directory. Takes precedence overTASKDATA_ROOT.
- Plugin mode (
- Collection Isolation (Namespacing):
- Manual (
BACKLOG_NAMESPACE): Explicitly sets the collection name (default istasks). - Automatic (
BACKLOG_AUTO_NAMESPACE=true): Derives the collection name from the CWD slug (same logic asTASKDATA_ROOT). Useful when sharing a singleTASKDATAdirectory (e.g. S3 bucket) across multiple projects.
- Manual (
If neither TASKDATA nor TASKDATA_ROOT is set, the server refuses to start. The server auto-creates directories and collections on first run.
Architecture
Claude Code / Agent Teams
│ (MCP stdio)
▼
┌──────────────┐
│ MCP Server │ TypeScript, @modelcontextprotocol/sdk
│ (stdio) │ Zod input schemas, structured output
└──────┬───────┘
│ direct function calls
▼
┌──────────────┐
│ Engine │ Native TypeScript (src/engine/)
│ (AgentDB) │ defineSchema, collections, blob storage, opslog underneath
└──────────────┘
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 · 277 lines · 4,036 tokens per session scan A 332e7a6c1d21
backlog CLAUDE.md is an instructions file published in the GitHub repository backloghq/backlog (5 stars, last pushed 3mo ago), licensed MIT. It adds 4,036 tokens to every session, about $0.0202 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
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.