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/lint111/hacknplan-mcp/claude-mdgit clone --depth 1 https://github.com/Lint111/hacknplan-mcpWrote 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/lint111/hacknplan-mcp/claude-md)<a href="https://agentmods.dev/instructions/lint111/hacknplan-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lint111/hacknplan-mcp/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 | $0.01943 | $0.01943 |
| Opus 5 | $0.00971 | $0.00971 |
| Sonnet 5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
hacknplan-mcp 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 3d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
HacknPlan MCP Server - A Model Context Protocol server providing a pure API wrapper for the HacknPlan project management API. Enables AI assistants to manage game development projects, sprints, tasks, and design documents.
Version: 7.2.0 Language: 100% TypeScript (ESM modules) Runtime: Node.js 18+
Build & Development Commands
npm install # Install dependencies
npm run build # Compile TypeScript to dist/
npm run watch # Auto-rebuild on changes
npm run dev # Development mode with tsx (hot reload)
npm test # Build and run all tests
npm run clean # Remove dist/ directory
Testing
Tests use Node.js built-in test runner. Run npm test which builds first then executes:
dist/index.test.js- Unit tests (cache, transactions, search, batching)dist/tool-integration.test.js- Integration tests for tool workflows
Additional integration tests are available in tests/integration/:
- Test files:
test-*.js(deletion, name resolution, workflow shortcuts, etc.) - Test fixtures:
tests/fixtures/(sample data files) - Test scripts:
tests/scripts/(setup and runner scripts)
Running the Server
# Direct execution (requires HACKNPLAN_API_KEY env var)
HACKNPLAN_API_KEY=your-key node dist/index.js
# With Claude Code
claude mcp add hacknplan -s user -e HACKNPLAN_API_KEY=key -- node /path/to/dist/index.js
Architecture
Module Organization
src/
├── index.ts # MCP server entry point, HTTP client, main server setup
├── api/ # API-layer utilities
│ ├── metadata.ts # Project metadata caching (stages, categories, tags)
│ ├── search.ts # Multi-criteria work item search
│ └── templates.ts # Work item templates (bug-report, feature, research)
├── core/ # Infrastructure
│ ├── cache.ts # LRU cache with TTL support
│ ├── client.ts # HTTP client helpers (used by some modules)
│ └── transaction.ts # Atomic operations with rollback
├── cache/ # Specialized caches
│ ├── staging-cache.ts # 2-step deletion confirmation staging
│ ├── recovery-cache.ts # Persistent LRU cache for deleted item recovery
│ └── time-tracking-cache.ts # Automatic work session time tracking
├── tools/ # MCP tool implementations (one file per domain)
│ ├── registry.ts # Tool registration system with duplicate detection
│ ├── types.ts # ToolDefinition, ToolContext, ToolRegistry types
│ ├── projects.ts # Project CRUD + metrics
│ ├── boards.ts # Sprint/board management
│ ├── work-items.ts # Tasks/bugs/features CRUD
│ ├── deletion-confirmation.ts # Batch delete staging/confirmation
│ ├── deletion-recovery.ts # Recovery cache management tools
│ ├── advanced.ts # Slim variants, batch ops, summaries
│ └── ... # Other domain tools
├── types/ # Type definitions
│ ├── hacknplan.ts # HacknPlan API types
│ ├── deletion.ts # Deletion staging types
│ └── recovery.ts # Recovery cache types
└── utils/ # Shared utilities
├── batch.ts # Generic batch operation wrapper
├── pagination.ts # Pagination helpers
├── resolution.ts # ID/name resolution (tag names → IDs)
├── validation.ts # Input validation
└── errors.ts # Error handling utilities
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.
- 3d ago First seen · 181 lines · 1,943 tokens per session scan A 5646d9fb5166
hacknplan-mcp CLAUDE.md is an instructions file published in the GitHub repository Lint111/hacknplan-mcp (6 stars, last pushed 8mo ago), licensed MIT. It adds 1,943 tokens to every session, about $0.0097 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.