yao-meta-skill is a system for creating, testing, packaging, reviewing, and governing reusable skills for AI agents. It helps teams turn repeatable workflows into portable skill packages and track their quality and releases, with the catalogue entry covering its own skill and instruction.
Borrowing it
Nothing to install: this file belongs to yaojingang/yao-meta-skill. 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/yaojingang/yao-meta-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/yaojingang/yao-meta-skillWrote 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/yaojingang/yao-meta-skill/agents-md)<a href="https://agentmods.dev/instructions/yaojingang/yao-meta-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/yaojingang/yao-meta-skill/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 5.1 | $0.03710 | $0.03710 |
| Opus 5 | $0.01855 | $0.01855 |
| Sonnet 5 | $0.00742 | $0.00742 |
| Haiku 4.5 | $0.00371 | $0.00371 |
Grade C, and why
yao-meta-skill AGENTS.md scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Clean test-only scratch directories after verification with `find tests -maxdepth 1 \( -name 'tmp' -o -name 'tmp_*' \) -type d -exec rm -rf {} +`. Do not clean unrelated untracked files. How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Project Map
yao-meta-skill is the source repository for the Yao Meta Skill / Skill OS. Keep the root SKILL.md lean and route depth through the existing project layers:
SKILL.md: public trigger surface, compact workflow, and Skill OS gates.references/: stable method doctrine and operating guidance.scripts/: executable logic, report generators, compilers, gates, and CLI entrypoints.evals/: trigger, output, packaging, semantic, and regression fixtures.skill-ir/: platform-neutral skill contract and examples.agents/interface.yaml: portable runtime and trust metadata.security/: script, dependency, network, permission, and trust policies.registry/: package metadata, installability evidence, and compatibility metadata.skill_atlas/: portfolio catalog, route overlap, ownership, stale-skill, and dependency evidence.reports/: generated review, trust, conformance, registry, overview, and release evidence.docs/: durable public docs such as migration notes and localized READMEs.
Verification
Use make ci-test as the default full verification command before calling a change done. For focused work, run the smallest relevant target first, then finish with make ci-test when generated artifacts, packaging, registry, trust, or report UI changed.
Common focused checks:
- CLI changes:
python3 tests/verify_yao_cli.py - Operator UX changes:
python3 tests/verify_operator_ux.py - Skill overview report changes:
python3 tests/verify_skill_overview.py - Review Studio changes:
python3 tests/verify_review_studio.py - Trust or script inventory changes:
python3 tests/verify_trust_check.py - Packaging or registry changes:
python3 tests/verify_package_verification.py && python3 tests/verify_registry_audit.py - Phase-one trigger/context changes:
python3 tests/verify_phase1_trigger_holdout.py - Provider output changes:
python3 tests/verify_output_provider_matrix.py
Trusted evidence runs
Use python3 scripts/yao.py evidence-build <skill_dir> for an isolated dry run. Add --publish only after source and generated evidence have been committed and the target worktree is clean. Publishing creates an immutable bundle under the target Skill's .yao/releases, refreshes canonical report mirrors, and updates reports/.current-run.json last.
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.
- 8d ago First seen · 165 lines · 3,710 tokens per session scan C 9478bf3a56dc
yao-meta-skill AGENTS.md is an instructions file published in the GitHub repository yaojingang/yao-meta-skill (2,599 stars, last pushed 21d ago), licensed MIT. It adds 3,710 tokens to every session, about $0.0186 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
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 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).
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.