agentmods.dev

execute

execute is a skill for Claude Code, Codex from hanyuancheung/llm-skill. It costs 1 tokens per session (1,104 once invoked), scanned A, original, MIT.

A meta-skill that chooses a suitable domain skill for a concrete task, follows its instructions, and records useful signals for later improvement.

In plain words
What is it for?
Use it when a user gives a task such as writing code, fixing a bug, researching, or answering a question.
Why use it?
It avoids manually searching through every skill and provides a standard way to start task execution.

Skill for Claude CodeCodex

not rated 22 4mo ago A scan 1 tokens original MIT
View the source file hanyuancheung/llm-skill
Install

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.

agentmods
npx agentmods add skills/hanyuancheung/llm-skill/execute
Any agent
npx skills add hanyuancheung/llm-skill --skill execute
Clone the repo
git clone --depth 1 https://github.com/hanyuancheung/llm-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for execute

README.md
[![agentmods](https://agentmods.dev/badge/skills/hanyuancheung/llm-skill/execute.svg)](https://agentmods.dev/skills/hanyuancheung/llm-skill/execute)
Your own site
<a href="https://agentmods.dev/skills/hanyuancheung/llm-skill/execute"><img src="https://agentmods.dev/badge/skills/hanyuancheung/llm-skill/execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 1 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,104 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00001 $0.01104
Opus 5 $0.00000 $0.00552
Sonnet 5 $0.00000 $0.00221
Haiku 4.5 $0.00000 $0.00110

Measured 5d ago against content hash 0bd890bd5b47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute 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 5d 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.

skills/execute/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

execute — Execution Meta-Skill

What

Select the right domain skill from the AGENT.md routing table, complete the task, and passively collect distillable signals as raw material for the next distill pass.

When to use

  • ✅ User gives a concrete task (write code, fix a bug, research, answer a question).
  • ✅ An existing skill's triggers match the intent.

When NOT to use

  • ❌ The discussion is about the skill system itself (hand off to distill or guide).
  • ❌ Pure small talk with no executable action.

How (SOP)

  1. Read the Schema, not the whole library. Open section 2 of AGENT.md. Do NOT ls skills/ or batch-read all SKILL.md files.

  2. Pick ≤ 3 candidates. Match keywords, file_globs, intents against the user input. Prefer status: active over experimental on ties.

  3. Lazy load. read_file only the chosen SKILL.md. If it links to references/*.md, load on demand.

  4. Run pre hooks (see AGENT.md §10). For each hook in declared order, evaluate when; apply action:

    • skip → drop this skill silently, try next candidate.
    • warn → surface to user, continue.
    • proceed → continue.
    • run-script:<path> → execute; non-zero exit = violation, treat as hook failure.

  5. Execute the task. Follow the chosen skill's How section strictly. If a skill conflicts with user intent, user wins, and log the conflict into distill-candidates.

  6. Collect distillable signals (key). Maintain a distill-candidates list during execution. Log entries for:

    • New pitfall: an error/ambiguity the skill did not warn about.
    • Better practice: a superior approach beyond what is recorded.
    • Gap: no skill matched; you solved it with ad-hoc reasoning that felt reusable.
    • Conflict: skill-vs-skill or skill-vs-reality.
    • Correction: a step in the skill turned out to be inaccurate.

  7. Run post hooks before finishing (see AGENT.md §10.4–§10.5).

    • Always evaluate the default should-distill: if distill-candidates is non-empty, propose invoking distill.
    • Then run declared post hooks in order. Enforce require-validator strictly: a failing scripts/validate.py blocks the task report.

Read the full file on GitHub · 102 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago First seen · 102 lines · 1 tokens per session scan A 0bd890bd5b47

Subscribe to this mod's changes

execute is a skill published in the GitHub repository hanyuancheung/llm-skill (22 stars, last pushed 4mo ago), licensed MIT. It adds 1 tokens to every session and 1,104 once invoked, about $0.0000 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.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens