agentmods.dev

ai-task-master: Instructions file for Claude Code

CLAUDE.md

ai-task-master CLAUDE.md is an instructions file for Claude Code from developerz-ai/ai-task-master. It costs 4,297 tokens per session, scanned A, original, MIT.

A repository guide for AI agents editing the ai-task-master TypeScript codebase. It sets rules for code structure, tests, changes, comments and commit messages.

In plain words
What is it for?
Use it when an agent is adding or changing ai-task-master source code, tests, configuration or commits.
Why use it?
It gives coding agents consistent project rules and helps prevent untested modules, unnecessary abstractions and leftover designs.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is developerz-ai/ai-task-master's own configuration. It tells Claude Code how to work on ai-task-master itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-task-master configures →

not rated 5repo changed 2d ago A scan 4,297 tokens original MIT
View source ↗ developerz-ai/ai-task-master
Reuse

Borrowing it

Nothing to install: this file belongs to developerz-ai/ai-task-master. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/developerz-ai/ai-task-master/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/developerz-ai/ai-task-master

Made for: Claude Code.

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 ai-task-master CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/developerz-ai/ai-task-master/claude-md/github.svg)](https://agentmods.dev/instructions/developerz-ai/ai-task-master/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/developerz-ai/ai-task-master/claude-md"><img src="https://agentmods.dev/badge/instructions/developerz-ai/ai-task-master/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-task-master CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/developerz-ai/ai-task-master/claude-md"><img src="https://agentmods.dev/badge/instructions/developerz-ai/ai-task-master/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,297 This file is loaded in full into every session.
When invoked 4,297 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04297 $0.04297
Opus 5.5 $0.01719 $0.01719
Sonnet 5.5 $0.00859 $0.00859
Haiku 4.5 $0.00430 $0.00430

Measured 2d ago against content hash f5ed05a3d321, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-task-master 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| Runtime APIs | `node:fs/promises`, `node:child_process`/`execa`, web `fetch` |
CLAUDE.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Instructions for Claude when editing aitm source. Not for end users.

Non-negotiables (MUST / NEVER)

  • NEVER add bun test to CI — Bun's node:test shim mis-handles this suite across files (oven-sh/bun#5090); the node + integration jobs are the authoritative runners.
  • NEVER use an Anthropic SDK — inference is OpenRouter (OpenAI-compatible) only; Credentials reads OPENROUTER_API_KEY from env; no OAuth, no ~/.claude/.credentials.json.
  • NEVER expose aitm itself as an MCP server — it is only an MCP client (consumes external servers' tools via mcpServers in config).
  • NEVER keep a superseded design alive behind a flag, optional field, fallback branch, or rename alias — delete it; a failure's safety net is "do less", never "run the thing we just rejected" (two data-only exceptions under House style).
  • NEVER ship Bun.file / Bun.$ / Bun.spawn in production code — portability bug (fine in dev scripts and tests gated behind if (process.versions.bun)).
  • NEVER regenerate bun.lock inside a release PR, and never add a guard asserting lockfile workspace version fields match package.json — such a check is red after every release by construction (Releases below).
  • NEVER use git worktrees — work directly in this checkout.
  • MUST ship a paired *.test.ts with every module (two exemptions under Testing); no test, no merge.
  • MUST pass bin/check and run the suite under both bun test and node --test locally before every commit.
  • MUST keep provider wiring split exactly three ways — credentials/ + openrouter/ + config/provider-presets.ts; no fourth place constructs an OpenRouterClient.
  • MUST pass --admin when running or merging on the developerz-ai repos — main requires one approving review (Branch protection below).
  • NEVER add, stub, or leave TODOs for out-of-scope v1 features (mailbox, MCP server, webhooks, Docker) — stop and surface instead (Out of scope below).

Read the full file on GitHub · 147 lines

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. 2d ago Changed · +50 tokens per session f5ed05a3d321
  2. 4d ago Changed · +5 lines · +1,310 tokens per session 8c29c9b0e490
  3. 2mo ago First seen · 142 lines · 2,937 tokens per session scan A 7d5415ce1b6f

Subscribe to this mod's changes

ai-task-master CLAUDE.md is an instructions file published in the GitHub repository developerz-ai/ai-task-master (5 stars, last pushed 3d ago), licensed MIT. It adds 4,297 tokens to every session, about $0.0172 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

LLMai-agentautonomous-agentbuncligithub-automation
Related

ai-task-master CLAUDE.md compared with instructions from other repositories

ai-task-master CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ai-task-master CLAUDE.mddeveloperz-ai/ai-task-masterInstructions file53d agoMITA4,297Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode