claude-task-manager CLAUDE.md

claude-task-manager CLAUDE.md is an instructions file for coding agents from vibehat/claude-task-manager. It costs 527 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Code that enforces analysis, code reuse, structured planning, and ongoing compliance checks. It also defines rules for TypeScript, package management, and project architecture.

In plain words
What is it for?
Use it to guide feature work in the project, including codebase analysis, reuse checks, implementation planning, and validation.
Why use it?
Teams can lose consistency when contributors ignore existing components, create unnecessary files, or skip required planning steps. These instructions set shared working rules.

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/vibehat/claude-task-manager/claude-md
Clone the repo
git clone --depth 1 https://github.com/vibehat/claude-task-manager

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 claude-task-manager CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vibehat/claude-task-manager/claude-md.svg)](https://agentmods.dev/instructions/vibehat/claude-task-manager/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vibehat/claude-task-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/vibehat/claude-task-manager/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 527 This file is loaded in full into every session.
When invoked 527 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 $0.00527 $0.00527
Opus 5 $0.00264 $0.00264
Sonnet 5 $0.00105 $0.00105
Haiku 4.5 $0.00053 $0.00053

Measured yesterday against content hash 3863723c5274, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-task-manager 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.

CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Task Master AI Integration

@./.taskmaster/CLAUDE.md

Critical Rules

COMPLIANCE REQUIRED: This is a code reuse and consolidation project.

Mandatory Workflow

  1. Start with /analyze-first - Always analyze existing codebase before decisions
  2. Use /reuse-check before creating any new files or components
  3. Plan with /structured-plan for implementation
  4. Validate compliance throughout the process

Code Reuse Rules (violating ANY invalidates your response)

  • No new files without exhaustive reuse analysis
  • No rewrites when refactoring is possible
  • No generic advice - provide specific implementations
  • No ignoring existing codebase architecture
  • Extend existing services and components
  • Consolidate duplicate code
  • Reference specific file paths

Critical Thinking

USE BRUTAL HONESTY: Challenge assumptions, point out flaws, suggest alternatives. Being thoughtful > being agreeable.

Core Principles

  • Analyze before acting - Use workflow commands to understand existing code
  • Use pnpm only - Never npm or yarn
  • TypeScript strict mode - No any types, explicit interfaces
  • Feature-based architecture - Group by feature, not file type
  • Extend don't create - Prioritize reuse over new files

Tech Stack & Architecture

  • Framework: Next.js 15.2.4 + App Router + TypeScript strict
  • Styling: Tailwind CSS v4 + shadcn/ui + Radix UI
  • State: Zustand + React Hook Form + Zod
  • Structure: All code in /src - features, components, libs, hooks, stores

Essential Commands

pnpm dev             # Dev server
pnpm lint            # ESLint
pnpm typecheck       # TypeScript check
pnpm sync:taskmaster # Task sync
pnpm build           # Production build

Quick Reference

  • /analyze-first [feature] - Analyze before planning
  • /reuse-check [component] - Validate before creating
  • /structured-plan [request] - Full planning workflow
  • /spawn-reader [task] - Analysis agent
  • /spawn-maker [task] - Implementation agent

Read the full file on GitHub · 66 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. yesterday First seen · 66 lines · 527 tokens per session scan A 3863723c5274

Subscribe to this mod's changes

claude-task-manager CLAUDE.md is an instructions file published in the GitHub repository vibehat/claude-task-manager (21 stars, last pushed 1y ago), licensed MIT. It adds 527 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 2026-09-03.