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 lfyxhappy/lfcode --skill skill-creatorgit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/skill-creator)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/skill-creator"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/skill-creator/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/skills/lfyxhappy/lfcode/skill-creator"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/skill-creator.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 | $0.00051 | $0.00861 |
| Opus 5.5 | $0.00020 | $0.00344 |
| Sonnet 5.5 | $0.00010 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
skill-creator 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lfcode Skill Creator
Create only the files another Lfcode agent needs.
Choose the skill type
- Create a user-managed skill through Settings → Skills. The runtime resolves its managed root from the active Lfcode profile: ordinary installations use
~/.lfcode/skills/<skill-name>/; the pre-release installation usesC:\Users\liangfeng\.lfcodepre\skills/<skill-name>/. - Create a built-in skill under
packages/lfcode/src/skill/lfcode/.bundle/<skill-name>/when the skill should ship with Lfcode itself. - Keep the folder name identical to the skill
name. Use lowercase letters, digits, and hyphens only.
Create the minimum structure
Every skill needs SKILL.md with YAML frontmatter:
---
name: your-skill-name
description: Explain what the skill does and when Lfcode should use it.
---
Then write the body as operational instructions, not user-facing marketing text.
Write discoverable metadata
- Put all discovery guidance in
description, because that is what Lfcode sees before loading the body. - Describe both the task and the situations where the skill is useful. For deterministic automatic activation, write literal user phrases in the standard description:
用户提到解压、改后缀或拍平时使用。Do not add atriggersfield. A matching phrase activates the body directly; unrelated descriptive words do not. - Use only
nameanddescriptioninSKILL.mdfrontmatter. Do not add private activation fields such astriggers,auto_activate, orhidden. - Keep the body under 500 lines whenever possible. Put the essential safety rules and workflow in
SKILL.md; move long examples, history, API details and variant-specific guidance into directly linkedreferences/files. - Include
agents/openai.yamlfor user-facing metadata. Settings-created Skills generate it automatically; when authoring manually, keepinterface.display_name,interface.short_description, and a$skill-nameinterface.default_promptin sync withSKILL.md.
Add bundled resources only when they help
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.
- 1mo ago Changed · +2 lines · -12 tokens per session 4fe6bbcf1dd8
- 1mo ago First seen · 61 lines · 63 tokens per session scan A dd2ab5c61b3c
skill-creator is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 26d ago), licensed MIT. It adds 51 tokens to every session and 861 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.
Review changes (multi-agent)
Delegate read-only reviewers over the local changes/branch and consolidate findings.