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 agentmods add skills/lfyxhappy/lfcode/skill-creatornpx skills add lfyxhappy/lfcode --skill skill-creatorgit clone --depth 1 https://github.com/lfyxhappy/lfcodeWhat 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 | $0.00063 | $0.00653 |
| Opus 5 | $0.00032 | $0.00327 |
| Sonnet 5 | $0.00013 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00065 |
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 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 — 61 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 under
<lfcode-config-root>/skills/<skill-name>/when the skill should live in user data and be editable from the app. - 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 triggerable metadata
- Put all trigger guidance in
description, because that is what Lfcode sees before loading the body. - Describe both the task and the situations that should activate the skill.
- Keep the body concise. Move large references, scripts, or assets into files beside
SKILL.mdinside the same skill folder.
Add bundled resources only when they help
- Add
scripts/when the same deterministic steps would otherwise be rewritten each time. - Add
references/when the skill needs domain rules, APIs, or schemas that should be read only on demand. - Add
assets/when the skill needs templates or other files to copy or transform. - Do not create extra documentation like
README.mdor changelogs just for the skill.
Validate the right path
For a user-managed skill:
- Create or update files under
<lfcode-config-root>/skills/<skill-name>/. - Confirm the folder contains
SKILL.md. - Refresh skills in the app or call the skill discovery path again if needed.
For a built-in skill:
- Create or update files under
packages/lfcode/src/skill/lfcode/.bundle/<skill-name>/. - Remember that the bundle extractor copies everything under that folder into the runtime
lfcode-skills/<version>/skills/<skill-name>/directory. - Add or update a test in
packages/lfcode/test/skill/skill.test.tsso discovery proves the bundled skill exists and contains the expected instructions.
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 · 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 1mo ago), licensed MIT. It adds 63 tokens to every session and 653 once invoked, about $0.0003 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 2026-08-31.
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.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Check work (verify against criteria)
Verify an implementation against acceptance criteria with a reviewer and a tester.
Commit (clean, conventional)
Stage the right changes and write a clear, conventional commit message.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.