Borrowing it
Nothing to install: this file belongs to Ozzeron/prompt-pack. 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/Ozzeron/prompt-pack/main/AGENTS.mdgit clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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/ozzeron/prompt-pack/agents-md)<a href="https://agentmods.dev/instructions/ozzeron/prompt-pack/agents-md"><img src="https://agentmods.dev/badge/instructions/ozzeron/prompt-pack/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/ozzeron/prompt-pack/agents-md"><img src="https://agentmods.dev/badge/instructions/ozzeron/prompt-pack/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 | $0.00979 | $0.00979 |
| Opus 5 | $0.00490 | $0.00490 |
| Sonnet 5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
prompt-pack 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 3d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prompt-pack
A curated Agent Skills library for AI coding assistants. This repo ships prompts, not an application: nothing here builds or runs, so "working" means the linter, the hook tests, and the activation eval pass.
Stack
Markdown (the product) · Node ≥18 + yaml (tooling only) · Bash + PowerShell 5.1
installers · GitHub Actions
Triggers
- When the user asks to add or change a skill → read
docs/PROMPT-FORMAT.mdfirst, then the closest existing skill in the same category as a shape reference. Every skill edit needs ametadata.pp-versionbump in the same change; CI fails without it. - When you touch a
description:line → it is the activation surface, not a summary. Keep the what +Use when …+Not for …shape, keep it ASCII, and add or update cases inevals/descriptions/cases.yaml(one obvious query, one non-obvious phrasing, one near-miss that must route elsewhere). Then runnpm run eval:descriptions. - When a
SKILL.mdcrosses ~240 lines → do not trim wording. Move conditional material (templates, per-branch checklists, worked examples) intoreferences/*.mdand link it with an explicit load condition: "read X when Y". - When you change anything under
hooks/→npm run test:hooksmust cover the new decision AND the near-miss that must NOT fire. Guards fail open by contract; never add a code path that can throw pastguard(). - When you change
install.sh→ make the identical change ininstall.ps1. CI compares the two trees byte-for-byte on Windows, and the historical failure class is text encoding (BOM, CRLF, a regex eating the blank line after frontmatter). - When adding a skill to a profile → update both installers and the README profile table; the linter cross-checks all three and the counts.
Commands
npm run lint # format contract, spec conformance, cross-checks
npm run eval:descriptions # activation eval (deterministic; gates CI at 95%)
npm run test:hooks # what the enforcement hooks actually decide
npm run test:install-content # real installs into temp dirs, on-disk assertions
npm run check:version-bump # every changed skill bumped its version
./install.sh --list # profiles and targets
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.
- 3d ago First seen · 71 lines · 979 tokens per session scan A f9082000fc99
prompt-pack AGENTS.md is an instructions file published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 4d ago), licensed MIT. It adds 979 tokens to every session, about $0.0049 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 2026-09-06.
Other instructions, from other repositories
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
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.