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/piperbox/piper/claude-mdgit clone --depth 1 https://github.com/piperbox/piperWhat 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 | $0.02684 | $0.02684 |
| Opus 5 | $0.01342 | $0.01342 |
| Sonnet 5 | $0.00537 | $0.00537 |
| Haiku 4.5 | $0.00268 | $0.00268 |
Grade A, and why
piper 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 — 158 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.
What this is
An open-source, developer-first PaaS that gives you git push → live HTTPS URL on hardware you own — including a Raspberry Pi behind CGNAT. A single Go module produces multiple binaries:
piperd— the agent that runs on your box (control-plane, deployer, tunnel-client).piper-relay— the optional self-hostable cloud relay (SNI passthrough + tunnel server). Not built yet.piper— the CLI, a thin HTTP client topiperd.
Full design rationale lives in docs/superpowers/specs/ — read it before non-trivial work. Implementation plans live in docs/superpowers/plans/; work is delivered plan-by-plan, task-by-task, TDD-style. Plan 1 of 3 is the agent core, LAN-only (build a Dockerfile → run a container → health-check → serve at http://<app>.piper.localhost via managed Caddy, SQLite state). Plan 2 = relay + outbound tunnel + DNS-01 TLS. Plan 3 = GitHub webhook + PR-preview URLs.
Coding Principles
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
- Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
When editing existing code:
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 · 158 lines · 2,684 tokens per session scan A 05115a3d68ee
piper CLAUDE.md is an instructions file published in the GitHub repository piperbox/piper (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,684 tokens to every session, about $0.0134 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
homelab-monitor CLAUDE.md
Instructions for SikamikanikoBG/homelab-monitor, covering claude.md and conventions.
blackbox CLAUDE.md
Claude Code instructions for maxjb-xyz/blackbox, covering project: blackbox, core philosophy, technical standards, component breakdown and feature priorities (v1).
ODS CLAUDE.md
Claude Code instructions for Osmantic/ODS, covering claude.md, project overview, repository structure, build & development commands and linting and validation.
tianji AGENTS.md
Instructions for msgbyte/tianji, covering contributor guide, development tips, translation files, testing instructions and pr instructions.
meme-search CLAUDE.md
Instructions for neonwatty/meme-search, covering claude.md, 📁 file organization guidelines, 🤖 task agent usage guidelines, when to use task agents and documentation lookup pattern.
ecspresso CLAUDE.md
Instructions for kayac/ecspresso, covering claude.md, project overview, git workflow, build commands and build the binary.