Borrowing it
Nothing to install: this file belongs to timwukp/agent-skills-best-practice. 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/timwukp/agent-skills-best-practice/main/.kiro/steering/structure.mdgit clone --depth 1 https://github.com/timwukp/agent-skills-best-practiceWrote 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/timwukp/agent-skills-best-practice/structure)<a href="https://agentmods.dev/instructions/timwukp/agent-skills-best-practice/structure"><img src="https://agentmods.dev/badge/instructions/timwukp/agent-skills-best-practice/structure.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 | $0.00585 | $0.00585 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
agent-skills-best-practice structure.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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Structure
.
├── README.md / README.zh-CN.md # English and Chinese overviews
├── QUICKSTART.md # 5-minute Kiro quickstart
├── CONTRIBUTING.md # How to add skills, evals convention, PR process
├── install.sh # Copies skills into ~/.kiro/skills/
├── requirements.txt # Python tooling deps (pyyaml)
├── .github/workflows/ # CI: validate-skills.yml
├── .kiro/steering/ # This directory: product/tech/structure/conventions
├── skills/
│ ├── .claude-plugin/marketplace.json # Claude Code plugin marketplace config
│ ├── README.md # Skills collection docs
│ ├── CATALOG.md # All skills by category
│ ├── THIRD_PARTY_NOTICES.md # License attributions
│ ├── shared/ # Shared utilities (NOT skills — no SKILL.md)
│ │ └── test-runner/run_tests.py
│ ├── spec/ # Pointer to agentskills.io specification
│ ├── template/SKILL.md # Blank skill template
│ └── skills/ # One folder per skill
│ └── <skill-name>/
│ ├── SKILL.md # Required; frontmatter name == folder name
│ ├── evals/ # evals.json + trigger_evals.json (engineering skills)
│ ├── scripts/ # Optional executable code
│ ├── references/ # Optional docs loaded on demand
│ └── LICENSE.txt # Per-skill license where applicable
└── skills-workshop/ # Training materials
├── 01-fundamentals ... 06-resources-references/
│ └── slides.md, exercises.md, examples.md, templates.md, test-cases.md
├── hands-on-labs/ # LAB1-3
├── credit-estimation/ # Credit usage measurement materials
└── scripts/quick_validate.py # Validation script used by CI
Rules
- Everything under
skills/skills/must be a valid skill (a folder withSKILL.md). Shared code that is not a skill belongs inskills/shared/. - Skill folder name, frontmatter
name, and the CATALOG.md entry must stay in sync. - When adding a skill: create the folder, add it to
skills/CATALOG.md, add it to the right plugin group inskills/.claude-plugin/marketplace.json, and includeevals/.
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.
- yesterday First seen · 45 lines · 585 tokens per session scan A 84e713f3031b
agent-skills-best-practice structure.md is an instructions file published in the GitHub repository timwukp/agent-skills-best-practice (10 stars, last pushed 2d ago), licensed MIT. It adds 585 tokens to every session, about $0.0029 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
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.