Borrowing it
Nothing to install: this file belongs to nirelbaz/promptpit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nirelbaz/promptpit/main/CLAUDE.mdgit clone --depth 1 https://github.com/nirelbaz/promptpitWrote 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/nirelbaz/promptpit/claude-md)<a href="https://agentmods.dev/instructions/nirelbaz/promptpit/claude-md"><img src="https://agentmods.dev/badge/instructions/nirelbaz/promptpit/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 5.1 | $0.01711 | $0.01711 |
| Opus 5 | $0.00856 | $0.00856 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
promptpit 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 8d 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.
- `execFileSync` (not `execSync`) for git operations — prevents shell injection How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project
PromptPit (pit) — the composition layer for AI agent configuration. Bundles instructions, skills (Agent Skills spec), MCP servers, and env vars into one distributable stack that installs across Claude Code, Cursor, and other AI coding tools. Ten commands: pit init (scaffold a stack), pit collect (bundle configs), pit install (install stacks), pit uninstall (remove installed stacks), pit update (smart re-install with drift awareness), pit status (show what's installed and drifted), pit diff (text diff between installed and source), pit watch (live-sync skill changes), pit validate (check stack validity), and pit check (CI sync verification). Bare pit (no subcommand) opens an interactive TUI over the same core — grouped stack list, per-stack action menu, live validate / status-diff / open actions (v0.5.2+). Translation is the entry point, stack management is the product.
Commands
npm test # run tests (vitest)
npm run build # build dist/cli.js (tsup, ESM)
npm run lint # TypeScript strict mode check
npm run dev # watch mode build
Architecture
Adapter pattern with composition. Each AI tool is a plain object implementing PlatformAdapter. Shared utilities in adapter-utils.ts, not a base class.
src/
├── cli.ts # Commander.js entry point
├── commands/ # init.ts, collect.ts, install.ts, uninstall.ts, update.ts, status.ts, watch.ts, validate.ts, check.ts, diff.ts
├── adapters/ # claude-code.ts, cursor.ts, codex.ts, standards.ts, copilot.ts, registry.ts, types.ts, adapter-utils.ts, toml-utils.ts
├── core/ # stack.ts, skill-store.ts, manifest.ts, artifact-ops.ts, merger.ts, resolve.ts, reconcile.ts, select.ts, scripts.ts, security.ts, validate.ts
├── sources/ # github.ts (clone + auto-collect)
└── shared/ # schema.ts (Zod + types), markers.ts, utils.ts, io.ts, interactive.ts (@clack/prompts wrapper with TTY guard)
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.
- 8d ago First seen · 122 lines · 1,711 tokens per session scan A 410495fb96e0
promptpit CLAUDE.md is an instructions file published in the GitHub repository nirelbaz/promptpit (6 stars, last pushed 1mo ago), licensed MIT. It adds 1,711 tokens to every session, about $0.0086 per session on Opus 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.
Other instructions, from other repositories
skill-doctor data-exporter.instructions.md
Instructions for evilstar2016/skill-doctor, covering data-exporter, description, when to use and instructions.
skill-doctor github-automation.instructions.md
Instructions for evilstar2016/skill-doctor, covering github-automation, description, when to use and instructions.
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).