Borrowing it
Nothing to install: this file belongs to iker-gonzalez/antwork-skills. 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/iker-gonzalez/antwork-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/iker-gonzalez/antwork-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/instructions/iker-gonzalez/antwork-skills/claude-md)<a href="https://agentmods.dev/instructions/iker-gonzalez/antwork-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/iker-gonzalez/antwork-skills/claude-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/iker-gonzalez/antwork-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/iker-gonzalez/antwork-skills/claude-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 | $0.00822 | $0.00822 |
| Opus 5.5 | $0.00329 | $0.00329 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
antwork-skills CLAUDE.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 25d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
antwork-skills — Claude Code plugin for Antwork
A skill library that routes /antwork <command> to specialized skills, each encoding the
correct sequence of Antwork MCP tool calls. Distributed as a Claude Code plugin (bundled
.mcp.json → api.antwork.io/mcp) or via install.sh.
This repo is prompt content, not code. There is no build, no dependencies, and no test suite — correctness means the instructions are accurate about Antwork's MCP tools.
Layout
skills/<name>/SKILL.md— one directory per skill;SKILL.mdis the skill.agents/*.md— the 5 read-only audit subagents used by/antwork audit.templates/*.md— output templates skills render into.install.sh/uninstall.sh— non-plugin install path.claude-ai/build.sh— builds the claude.ai ZIP (oneantworkskill; every other skill and agent becomes a file underreferences/)..github/workflows/claude-ai-skill.ymlreruns it on every push tomainthat touches a packaged file and replaces the asset on theclaude-ai-skillrelease, whose URL antwork.io links to. Never rename that release or asset.README.md— the command table. It must stay in sync withskills/.
Changing a skill
Applies to every change, by hand or unattended.
- Base branch is
main— this repo has nodevbranch. Branch frommain, PR tomain. - Nothing to build or test. Verification is by inspection; say so in the PR body rather than implying automated coverage.
- Never invent MCP tool names, parameters, or response shapes. Every tool referenced in
a skill must exist in the Antwork MCP server. If the issue requires a tool you cannot
verify against
../antwork.io/agent-service/app/mcp/server.py, stop and say so rather than guessing — a plausible-looking wrong tool name is worse than no change. The server's tools change: on 2026-08-24 the stored voice profile went (prepare_voice_analysis,save_voice_analysis,voiceStale), and on 2026-10-03 eight tools were cut (antwork.io #1437). Both times these skills went on naming tools that no longer existed. - Facts with a source of truth get checked against it, not memory: character limits live in
../antwork.io/src/lib/platforms/common/platform-rules.json. clawhub/antwork/SKILL.mdis a self-contained copy of the core rules for OpenClaw's registry. A change to a rule inskills/usually needs the same change there.- Adding or renaming a skill means updating both
skills/<name>/SKILL.mdand the command table inREADME.md. A PR touching only one is incomplete. - Adding or removing a skill also means updating the
SKILLSlist ininstall.sh(a removed one goes on its retired list there, and stays inuninstall.shso old installs get cleaned up). Otherwise never touchinstall.sh,uninstall.sh, or.mcp.jsonunless the issue explicitly asks. - Single steps belong to the server, not here. Drafting one post, scheduling, media,
connections and comments are spelled out in the MCP server's
instructions=and tool descriptions. A skill that restates them only drifts (antwork-poster, -setup, -media and -engage were removed in 1.2.0 for that reason). Skills here are for multi-step workflows.
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.
- 25d ago Changed · +10 lines · +238 tokens per session 7f00f3682a59
- 27d ago First seen · 39 lines · 584 tokens per session scan A 121eacf664d9
antwork-skills CLAUDE.md is an instructions file published in the GitHub repository iker-gonzalez/antwork-skills (0 stars, last pushed 25d ago), licensed MIT. It adds 822 tokens to every session, about $0.0033 per session on Opus 5.5. 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 2026-10-04.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.