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/liqiongyu/agentpack/agents-mdgit clone --depth 1 https://github.com/liqiongyu/agentpackWrote 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/liqiongyu/agentpack/agents-md)<a href="https://agentmods.dev/instructions/liqiongyu/agentpack/agents-md"><img src="https://agentmods.dev/badge/instructions/liqiongyu/agentpack/agents-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 | $0.01011 | $0.01011 |
| Opus 5 | $0.00505 | $0.00505 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
agentpack 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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec Instructions
These instructions are for AI assistants working in this project.
Always open @/openspec/AGENTS.md when the request:
- Mentions planning or proposals (words like proposal, spec, change, plan)
- Introduces new capabilities, breaking changes, architecture shifts, or big performance/security work
- Sounds ambiguous and you need the authoritative spec before coding
Use @/openspec/AGENTS.md to learn:
- How to create and apply change proposals
- Spec format and conventions
- Project structure and guidelines
Keep this managed block so 'openspec update' can refresh the instructions.
Repository Guidelines
Project Structure & Module Organization
src/: Rust CLI (agentpack).templates/: embedded operator assets (Codex skill + Claude commands) used byagentpack bootstrap.tests/: unit tests + golden snapshots (tests/golden/).docs/: product/design docs (docs/PRD.md,docs/ARCHITECTURE.md,docs/SPEC.md,docs/BACKLOG.md).openspec/: proposal-driven changes + archived changes underopenspec/changes/archive/..github/: CI and GitHub templates.
Specs & Contracts
docs/SPEC.mdis the authoritative, implementation-level contract (CLI behavior,--jsonenvelopes, file formats).docs/JSON_API.mdanddocs/ERROR_CODES.mddefine the stable--jsonenvelope rules and error codes for automation.openspec/specs/is the OpenSpec “requirements slice”; changes go throughopenspec/changes/<change-id>/...and MUST stay consistent withdocs/SPEC.md.- If you change stable output (especially
--json), updatedocs/SPEC.md, OpenSpec deltas, and relevant snapshots undertests/golden/.- If you add a new mutating command, update
src/cli/util.rs(MUTATING_COMMAND_IDS),agentpack help --json, and guardrails tests (tests/cli_guardrails.rs).
- If you add a new mutating command, update
Build, Test, and Development Commands
just check: run the standard local/CI checks (preferred).cargo fmt --all -- --check: formatting (required).cargo clippy --all-targets --all-features -- -D warnings: lint (required).cargo test --all --locked: tests (required in CI).pre-commit install: install git hooks (one-time).pre-commit run -a: run repo hooks locally.agentpack completions <shell>: generate shell completions.openspec validate --all --strict --no-interactive: validate OpenSpec specs in CI-friendly mode.
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.
- 4d ago First seen · 67 lines · 1,011 tokens per session scan A cc5a3ac80354
agentpack AGENTS.md is an instructions file published in the GitHub repository liqiongyu/agentpack (18 stars, last pushed 6mo ago), licensed MIT. It adds 1,011 tokens to every session, about $0.0051 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 2026-08-30.
Other instructions, from other repositories
intelligent-terminal rust-wta.instructions.md
File-scoped conventions for the WTA Rust crate.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
sivtr AGENTS.md
AGENTS.md instructions for Ariestar/sivtr, covering ai agent instructions, project, commands, communication and working agreement.
sivtr CLAUDE.md
Claude Code instructions for Ariestar/sivtr, covering claude.md, project overview, development commands, workspace structure and key data types.
bifrost AGENTS.md
Instructions for bifrost-proxy/bifrost, covering bifrost 项目开发规则, 执行心法, 执行模式与完成定义, 任务模式判定 and 变更类型与验证路由（先判定，后执行）.
anda AGENTS.md
AGENTS.md instructions for ldclabs/anda, covering agents.md, scope, repository shape, working rules and runtime boundaries.