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/silupanda/pith/claude-mdgit clone --depth 1 https://github.com/SiluPanda/pithWhat 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 | $0.00610 | $0.00610 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
pith 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 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.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Pith Agent Instructions
This file provides context for AI agents (Claude Code, Cursor, etc.) working on the Pith codebase.
Project Overview
Pith is an AI-native task management system. Monorepo with 7 packages:
packages/core— Shared Zod schemas, types, and constantspackages/db— Drizzle ORM schema, migrations, PostgreSQL clientpackages/server— Fastify API server (all routes, auth, middleware)packages/ai— Vercel AI SDK integration (optional AI features)packages/mcp-server— MCP server (stdio + HTTP transports)packages/cli— Commander.js CLIpackages/web— React + Vite web UI
Key Commands
npm install # Install all dependencies
npm run dev # Start API server (port 3456)
npm test # Run all tests (128 tests)
npm run db:migrate # Run database migrations (from packages/db/)
npm run db:seed # Seed sample data
Architecture
- API: Fastify with Zod validation, JWT + API key auth, RBAC
- Database: PostgreSQL 16+ via Drizzle ORM
- MCP: @modelcontextprotocol/sdk with stdio and HTTP/SSE transports
- AI: Vercel AI SDK, provider-agnostic, graceful degradation
- Testing: Vitest + Fastify inject (no Supertest needed)
Database
Connection via DATABASE_URL env var. Tables: users, projects, tasks, comments, activities, agent_sessions, labels, views, webhooks, webhook_deliveries, task_links, time_entries.
Testing
Tests are in packages/server/src/__tests__/ and packages/mcp-server/src/__tests__/. Run with npm test. Tests use a real PostgreSQL database (no mocks). The cleanDatabase() helper truncates all tables between test groups.
Code Patterns
- Routes are in
packages/server/src/routes/as Fastify plugins - Response format:
success(data),paginated(items, total, limit, offset),error(code, message) - Auth:
authenticatehook +authorize(...roles)for RBAC - All list endpoints support pagination via
limitandoffsetquery params - Activity logging on task mutations (status_changed, priority_changed, assigned, etc.)
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.
- 2d ago First seen · 59 lines · 610 tokens per session scan A 4432e7ba9689
pith CLAUDE.md is an instructions file published in the GitHub repository SiluPanda/pith (8 stars, last pushed 5mo ago), licensed MIT. It adds 610 tokens to every session, about $0.0030 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
Kanera CLAUDE.md
Claude Code instructions for happendev/Kanera, covering purpose, repo shape, commands, backend rules and schema workflow.
Kanera AGENTS.md
AGENTS.md instructions for happendev/Kanera, a project described as: A polished project management tool with workspace-wide lists, labels and custom fields, automations, assigned work, realtime collaboration, REST API and MCP support.
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
autoharness AGENTS.md
Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.