OpenClaw Agent Skills is a shared repository of reusable workflows for coding agents working on OpenClaw projects. It provides skills for activities such as code-review closeout, behavior validation, session handoff, remote testing, transcript provenance, and viewing agent sessions. The catalogue entries are the project’s distributed skills and instruction.
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 skills add openclaw/agent-skills --skill readme-standardgit clone --depth 1 https://github.com/openclaw/agent-skillsWrote 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/skills/openclaw/agent-skills/readme-standard)<a href="https://agentmods.dev/skills/openclaw/agent-skills/readme-standard"><img src="https://agentmods.dev/badge/skills/openclaw/agent-skills/readme-standard.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01442 |
| Opus 5 | $0.00016 | $0.00721 |
| Sonnet 5 | $0.00007 | $0.00288 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
readme-standard 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 9d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
README Standard
One structure for every public README in the steipete and openclaw orgs. Load
this skill before writing or reviewing a README. The reference implementation
is openclaw/fs-safe — read its README
first if unsure what "good" looks like.
The spine
Every README answers, in order, with no detours:
- What is this? — one sentence a stranger understands.
- How do I use it? — smallest real install + a quickstart that proves the pitch.
- Progressively more complex — each section assumes the previous one; deep
reference material moves to
docs/(or the docs site) and gets linked.
Concretely:
# <name> <one emoji> — <playful tagline, one line>
<badge row>
<1–2 sober sentences: what it is, who it is for. No adjectives doing the work
nouns should do.>
<OPTIONAL: one small code/terminal sample (≤10 lines) that demonstrates the
core value. If one sample can prove the pitch, put it here.>
## Install ← smallest path first (brew/npm/npx), alternatives after
## Quick start ← 60 seconds to first success; commands must actually run
## <core sections> ← 2–6 sections, each one level deeper than the last
## Development ← build/test/lint in ≤10 lines, link CONTRIBUTING if present
## License ← one line
Rules
- Title/tone: playful tagline with one emoji is welcome; the body is sober. First paragraph states plainly what the tool does and for whom.
- No feature walls. A list of >6 marketing bullets is a smell. Fold real capabilities into the sections where they are demonstrated.
- No changelog-speak ("now supports", "new in 3.2", "coming soon"). The
README describes the present tense of the tool. Version-specific migration
notes live in the changelog or
docs/. - Length: aim ≤250 lines for tools/libraries, ≤350 for large surfaces.
Anything beyond that moves to
docs/with a link. Exhaustive command/flag references belong indocs/or the docs site, never in the README — a summary table with links is fine. - Progressive depth: a reader should be able to stop after any section and have a working setup for that level of use.
- Screenshots/banners: keep existing project art. Apps and TUIs should show one screenshot near the top. Compress; no >500 KB images.
- Docs sites win: when the repo has a docs site (fs-safe.io, gitcrawl.sh, …), the README is a front door, not a mirror. Link, don't duplicate.
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.
- 9d ago First seen · 125 lines · 33 tokens per session scan A 63eb15336316
readme-standard is a skill published in the GitHub repository openclaw/agent-skills (1,079 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,442 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…