Borrowing it
Nothing to install: this file belongs to mtthsnc/tempest. 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/mtthsnc/tempest/main/AGENTS.mdgit clone --depth 1 https://github.com/mtthsnc/tempestWrote 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/mtthsnc/tempest/agents-md)<a href="https://agentmods.dev/instructions/mtthsnc/tempest/agents-md"><img src="https://agentmods.dev/badge/instructions/mtthsnc/tempest/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mtthsnc/tempest/agents-md"><img src="https://agentmods.dev/badge/instructions/mtthsnc/tempest/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01009 | $0.01009 |
| Opus 5.5 | $0.00404 | $0.00404 |
| Sonnet 5.5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
tempest 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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents (and humans) working on the tempest repo. For what it does and how to install it, see README.md; for the cross-harness design, see docs/ARCHITECTURE.md.
What this repo is
tempest is a software factory: a set of opinionated build workflows — plan → build → review → test → ship → reflect — shipped as portable Agent Skills that run identically on Claude Code and pi. The skills are the product; the manifests and installer are thin wiring around one shared source tree. It contains no personal data.
Golden rules
- One source, two harnesses. Every skill is authored once under
plugins/tempest/skills/<name>/SKILL.mdfollowing the Agent Skills standard. Never fork a skill per harness. If a harness needs something different, express it in the install wiring, not in duplicated content. - The conformance gate is law.
./scripts/validate.shmust pass before any commit;./tests/run.shbefore any push. CI runs both. - Skill
description= trigger, not summary. Start every skill description with "Use when…" and describe when to invoke, never the workflow. A description that summarizes the steps makes agents follow the summary instead of reading the skill body. (The gate enforces the "Use when" prefix.) - Commands are portable or they don't ship. A
commands/<verb>.mdmust use only the arg subset both harnesses share ($ARGUMENTS,$1–$9) and carry adescription. Pi-only (${1:-def},${@:N}) and Claude-only (allowed-tools,model) syntax is flagged by the gate. - No hardcoded user, home, or project paths. Default to
~/.claude/…,~/.pi/…,~/.agents/…(resolve per user) or read from settings. A grep for/home/in tracked files returns nothing.
Layout
.claude-plugin/marketplace.json Claude marketplace index (lists the plugin)
plugins/tempest/
.claude-plugin/plugin.json Claude plugin manifest
skills/<name>/SKILL.md THE skills (Agent Skills standard) — author once
commands/<verb>.md thin slash entry points (also pi prompt templates)
package.json pi package manifest (pi.skills / pi.prompts)
AGENTS.md CLAUDE.md -> AGENTS.md instructions (Claude reads CLAUDE.md; pi reads either)
install.sh uninstall.sh idempotent wiring into ~/.agents, ~/.claude, ~/.pi
scripts/validate.sh conformance gate
tests/run.sh sandbox install + manifest/skill assertions
docs/ARCHITECTURE.md the cross-harness design
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.
- 1mo ago First seen · 69 lines · 1,009 tokens per session scan A 18604909736d
tempest AGENTS.md is an instructions file published in the GitHub repository mtthsnc/tempest (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,009 tokens to every session, about $0.0040 per session on Opus 5.5. 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).
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.