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/vibehat/claude-task-manager/claude-mdgit clone --depth 1 https://github.com/vibehat/claude-task-managerWrote 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/vibehat/claude-task-manager/claude-md)<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>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 | $0.00527 | $0.00527 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
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.
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
- Start with
/analyze-first- Always analyze existing codebase before decisions - Use
/reuse-checkbefore creating any new files or components - Plan with
/structured-planfor implementation - 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
anytypes, 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
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 · 66 lines · 527 tokens per session scan A 3863723c5274
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.
Other instructions, from other repositories
task-orchestrator CLAUDE.md
Instructions for jpicklyk/task-orchestrator, covering project: mcp task orchestrator, build commands, docker (most common), architecture and modes of operation.
vibecode-pro-max-kit AGENTS.md
Instructions for withkynam/vibecode-pro-max-kit, covering agents.md, riper-5 spec-driven development system, shared development protocols, orchestrator role (main codex session) and repository context.
spec-driven-development-template sdd-specs.instructions.md
Instructions for juanklagos/spec-driven-development-template, a project described as: Operational SDD framework with AI guidance, GitHub Spec Kit workflows, and MCP support.
aicontext copilot-instructions.md
Copilot instructions for zahardev/aicontext, covering project rules and prompts.
leonidas CLAUDE.md
Instructions for JeremyDev87/leonidas, covering claude.md, what is leonidas, commands, architecture and module system.
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).