agentmods.dev

lfcode-plugin-author

lfcode-plugin-author is a skill for Claude Code, Codex from lfyxhappy/lfcode. It costs 45 tokens per session (428 once invoked), scanned A, original, MIT.

A guided workflow for creating, checking, previewing, exporting, and installing Lfcode plugins, which are add-ons that extend a coding tool.

In plain words
What is it for?
It helps create tool or integration plugins with the public SDK, run validation and tests, review a preview, and install only after confirmation.
Why use it?
It keeps plugin work in a managed workspace, catches validation problems, and prevents installation without explicit approval.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 26d ago A scan 45 tokens original MIT

Good fit It helps create tool or integration plugins with the public SDK, run validation and tests, review a preview, and install only after confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lfyxhappy/lfcode/lfcode-plugin-author
View source ↗ lfyxhappy/lfcode
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.

Any agent
npx skills add lfyxhappy/lfcode --skill lfcode-plugin-author
Clone the repo
git clone --depth 1 https://github.com/lfyxhappy/lfcode

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 lfcode-plugin-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/lfyxhappy/lfcode/lfcode-plugin-author/github.svg)](https://agentmods.dev/skills/lfyxhappy/lfcode/lfcode-plugin-author)
Your own site
<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/lfcode-plugin-author"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/lfcode-plugin-author/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.

agentmods 80×15 button for lfcode-plugin-author

Your own site · 80×15
<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/lfcode-plugin-author"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/lfcode-plugin-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 428 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.00428
Opus 5.5 $0.00018 $0.00171
Sonnet 5.5 $0.00009 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 1mo ago against content hash 844de09983f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lfcode-plugin-author 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.

packages/lfcode/src/skill/lfcode/.bundle/lfcode-plugin-author/SKILL.md · 35 lines

What it actually says

Lfcode Plugin Author

Use the managed authoring workflow. Never write directly into the installed plugin library.

Allowed scope

  • Create only tool or integration plugins.
  • Work only through plugin_author inside the managed workspace for the requested plugin ID.
  • Use the public @lfcode-ai/plugin SDK. Do not import private runtime modules from packages/lfcode.
  • Do not claim official or bundled trust. Model-authored plugins are external.

Required workflow

  1. Call plugin_author with create to create a minimal workspace.
  2. Inspect and edit only that workspace with normal file tools.
  3. Call plugin_author with validate; fix every blocking error.
  4. Add a focused real test when the plugin contains behavior beyond the generated placeholder.
  5. Call plugin_author with preview and show the full review report to the user.
  6. Stop and request explicit confirmation. Do not treat the request to create the plugin as confirmation to install it.
  7. Only after confirmation, pass the returned token to plugin_manage with import_commit.
  8. Verify the installed plugin appears in plugin_manage list and is visible from the next provider turn.

Prohibited actions

  • Do not write <lfcode-data>/plugins/library, current.json, or registry.json directly.
  • Do not bypass preview tokens, fabricate digests, extend expiry, or reuse a consumed token.
  • Do not generate provider, ui, theme, runtime, or mixed plugins in the first authoring version.
  • Do not add native executables, install scripts, dynamic libraries, credentials, tokens, or machine-specific absolute paths.
  • Do not automatically approve, enable, replace, uninstall, or export outside the managed workflow.
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. 1mo ago First seen · 35 lines · 45 tokens per session scan A 844de09983f9

Subscribe to this mod's changes

lfcode-plugin-author is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 26d ago), licensed MIT. It adds 45 tokens to every session and 428 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 2026-09-05.

Building agentsaibuncoding-agentdesktop-appdeveloper-toolselectron
Related

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.

AuraVixStudio/caelo · 48 tokens

Best of N (parallel attempts)

Delegate N parallel subagents on the same task, then pick the best result.

AuraVixStudio/caelo · 23 tokens

Design doc (write -> review loop)

Draft a design document and iterate writer/reviewer subagents until consensus.

AuraVixStudio/caelo · 22 tokens

Implement (multi-agent loop)

Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.

AuraVixStudio/caelo · 24 tokens

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.

AuraVixStudio/caelo · 36 tokens

Review changes (multi-agent)

Delegate read-only reviewers over the local changes/branch and consolidate findings.

AuraVixStudio/caelo · 20 tokens