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/kanocifer/devtaskmcp/claude-mdgit clone --depth 1 https://github.com/KanoCifer/DevTaskMcpWhat 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 | $0.01025 | $0.01025 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
DevTaskMcp 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 yesterday.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project
DevTaskMcp is an MCP server (Python, FastMCP) that wraps the kanocifer.chat dev-task API as Task Document v3 tools for AI agents. It implements a "frontier" pattern — agents claim and execute the next ready task from a kanban board. The v3 protocol collapses all long-form text into a single detail Markdown body; structured fields are passed as inline tool parameters.
Commands
# Run the MCP server (streamable-http, binds 0.0.0.0:8003, endpoint /mcp/)
uv run python -m devtask_mcp.server
# Docker deploy
docker compose up --build
# Run the test suite
uv run --group dev python -m pytest tests -q
Server env: MCP_HOST/MCP_PORT (default 0.0.0.0:8003), MCP_AUTH_TOKEN (static Bearer token; empty disables app-level auth). The container binds loopback only — a reverse proxy in front terminates TLS.
Environment
.env (gitignored, copy from .env.example) provides:
DEVTASK_API_KEY— required, Bearer for the API.DevTaskClientraisesRuntimeErrorat construction if empty.DEVTASK_API_BASE— defaults tohttps://api.kanocifer.chat/api/v3.
Code style
from __future__ import annotationsin every source file (PEP 604 union syntax).- Google-style docstrings with
Args:sections. - Logger name:
"devtask-mcp".
Critical: Chinese literal enums
Task model enum values are Chinese strings, not English constants. Validating at the Python boundary prevents bad values from wasting API round-trips:
| Field | Canonical values |
|---|---|
TaskType |
"问题", "功能需求", "优化", "技术债" |
TaskPriority |
"P0 紧急", "P1 高", "P2 中", "P3 低" |
TaskStatus |
"待评估", "待排期", "进行中", "已搁置", "已完成" |
TaskScope |
free-form str, recommended format "<层>-<技术>" e.g. "前端-React" |
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.
- yesterday First seen · 73 lines · 1,025 tokens per session scan A e5873df9e5ef
DevTaskMcp CLAUDE.md is an instructions file published in the GitHub repository KanoCifer/DevTaskMcp (0 stars, last pushed 7d ago), licensed MIT. It adds 1,025 tokens to every session, about $0.0051 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.