agentmods.dev

piper AGENTS.md

Project instructions for working on Piperbox/Piper, including its coding rules, tests, runtime setup, and delivery process.

In plain words
What is it for?
Reading the authoritative CLAUDE.md file, running Go formatting, vetting, tests, cross-compilation, and using the project’s fake runtime for suitable unit tests.
Why use it?
They give an agent the project-specific requirements needed to make compatible changes and verify them before claiming completion.

Instructions file for CodexOpenCode

10 2d ago A scan 385 tokens original Apache-2.0
View the source file piperbox/piper
Install

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.

agentmods
npx agentmods add instructions/piperbox/piper/agents-md
Clone the repo
git clone --depth 1 https://github.com/piperbox/piper

Made for: Codex, OpenCode.

Per session 385 This file is loaded in full into every session.
When invoked 385 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00385 $0.00385
Opus 5 $0.00192 $0.00192
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured 2d ago against content hash 8b623bc59e55, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

piper AGENTS.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.

AGENTS.md · 11 lines

What it actually says

AGENTS.md

Read CLAUDE.md in full first — it is the authoritative source for coding principles, commands, constraints, layering, and branch/PR/issue workflow. This file only captures high-signal facts an agent would otherwise get wrong that aren't obvious from filenames or CLAUDE.md.

  • Single package: go test ./internal/store/.... Single test: go test ./internal/store -run TestName.
  • Before claiming work is done, run the full CI sequence: gofmt -l . (it must print nothing), go vet ./..., make test, then make cross. make test and make cross alone do not catch formatting or vet failures.
  • For unit tests of code that depends on runtime.Runtime, use internal/runtime.FakeRuntime from internal/runtime/fake.go. Real Docker is reserved for Docker integration and e2e tests, which must skip cleanly when Docker is unavailable.
  • Runtime environment configuration belongs in internal/config; production packages must not call os.Getenv inline.
  • TestEndToEndDeploy failing with "no response through Caddy" is usually not a code bug: any other Caddy holding :80/:2019 serves the request from its own empty route table, and Caddy's SO_REUSEPORT lets piperd's embedded instance bind alongside it with no error. Run lsof -nP -iTCP:80 -iTCP:2019 -sTCP:LISTEN and kill any stray caddy/piperd first.
  • The layering rule is enforced by test/arch. Adding an internal/ package means giving it a rank there; if a change needs that map edited to pass, check whether the new import is the actual mistake.
Changes

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.

  1. 2d ago First seen · 11 lines · 385 tokens per session scan A 8b623bc59e55

Subscribe to this mod's changes

piper AGENTS.md is an instructions file published in the GitHub repository piperbox/piper (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 385 tokens to every session, about $0.0019 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.

deploymentdockerhomelabpaasself-hosted
Related

Other instructions, from other repositories

homelab-monitor CLAUDE.md

Instructions for SikamikanikoBG/homelab-monitor, covering claude.md and conventions.

SikamikanikoBG/homelab-monitor · 138 tokens

blackbox CLAUDE.md

Claude Code instructions for maxjb-xyz/blackbox, covering project: blackbox, core philosophy, technical standards, component breakdown and feature priorities (v1).

maxjb-xyz/blackbox · 480 tokens

ODS CLAUDE.md

Claude Code instructions for Osmantic/ODS, covering claude.md, project overview, repository structure, build & development commands and linting and validation.

Osmantic/ODS · 2,157 tokens

tianji AGENTS.md

Instructions for msgbyte/tianji, covering contributor guide, development tips, translation files, testing instructions and pr instructions.

msgbyte/tianji · 228 tokens

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.

neonwatty/meme-search · 2,697 tokens

ecspresso CLAUDE.md

Instructions for kayac/ecspresso, covering claude.md, project overview, git workflow, build commands and build the binary.

kayac/ecspresso · 931 tokens