agentmods.dev

lenny_skills_plus: Instructions file for Codex

AGENTS.md

lenny_skills_plus AGENTS.md is an instructions file for Codex, OpenCode from liqiongyu/lenny_skills_plus. It costs 1,068 tokens per session, scanned A, original, Apache-2.0.

Instructions for a repository that creates portable skill packs for coding agents. A skill pack is a reusable set of agent instructions, and the repository supports both OpenAI Codex and Claude Code.

In plain words
What is it for?
They help create, validate, mirror, and release skill packs, while checking documentation, metadata, and repository conventions.
Why use it?
They define where skills belong, which files each pack needs, and how to keep generated content consistent and testable.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; reads ~/.codex paths.

This is liqiongyu/lenny_skills_plus's own configuration. It tells Codex and OpenCode how to work on lenny_skills_plus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lenny_skills_plus configures →

not rated 53repo +1 5mo ago A scan 1,068 tokens original Apache-2.0
View source ↗ liqiongyu/lenny_skills_plus
Reuse

Borrowing it

Nothing to install: this file belongs to liqiongyu/lenny_skills_plus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/liqiongyu/lenny_skills_plus/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/liqiongyu/lenny_skills_plus

Made for: Codex, OpenCode.

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 lenny_skills_plus AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/liqiongyu/lenny_skills_plus/agents-md/github.svg)](https://agentmods.dev/instructions/liqiongyu/lenny_skills_plus/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/liqiongyu/lenny_skills_plus/agents-md"><img src="https://agentmods.dev/badge/instructions/liqiongyu/lenny_skills_plus/agents-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.

agentmods 80×15 button for lenny_skills_plus AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/liqiongyu/lenny_skills_plus/agents-md"><img src="https://agentmods.dev/badge/instructions/liqiongyu/lenny_skills_plus/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,068 This file is loaded in full into every session.
When invoked 1,068 The same file — it is already loaded in full.
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 $0.01068 $0.01068
Opus 5.5 $0.00427 $0.00427
Sonnet 5.5 $0.00214 $0.00214
Haiku 4.5 $0.00107 $0.00107

Measured 2mo ago against content hash 92724cc5a1b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lenny_skills_plus AGENTS.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 2mo 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.

AGENTS.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lenny Skills Plus — Agent Instructions

You are working in a repository that serves two purposes:

  1. A curated library of agent-executable skill packs under skills/ (installable from GitHub Releases).
  2. A skillpack factory: tooling + workflows to convert RefoundAI “Lenny skills” into reliable, portable skill packs.

Primary goals:

  1. Produce high-density, testable Agent Skills skill packs (not essays).
  2. Ensure outputs are compatible with both OpenAI Codex and Claude Code (use the common Agent Skills subset).
  3. All generated skill pack content must be written in English.

Start here (repo docs):

Repo conventions

Canonical skill packs (tracked)

  • Canonical skills live under skills/<skill-slug>/ (tool-agnostic, tracked in git).
  • Each skill pack must include:
    • skillpack.json (metadata used by this repo’s tooling + releases)
    • SKILL.md (Agent Skills entrypoint; YAML frontmatter with name, description)
    • README.md (human-friendly overview + example prompts)
    • references/ core set:
      • INTAKE.md, WORKFLOW.md, TEMPLATES.md, CHECKLISTS.md, RUBRIC.md, SOURCE_SUMMARY.md, EXAMPLES.md
    • scripts/ (optional; only when it materially improves determinism)

Tool mirrors (generated, not tracked)

  • .codex/skills/<skill-slug>/ and .claude/skills/<skill-slug>/ are generated mirrors for tool auto-discovery and are ignored by git.
  • Generate/update via: python3 scripts/mirror_skills.py --overwrite.

Upstream sources (usually local-only)

  • Keep bulk-downloaded Refound sources out of git by default.
  • Store sources under:
    • sources/refound/raw/<slug>/SKILL.md (preferred), or
    • sources/refound/raw/<slug>/page.html (fallback).
  • (Optional) Fetch sources in bulk: python3 skills/lenny-skillpack-creator/scripts/fetch_refound_skills.py --out sources/refound/raw

Read the full file on GitHub · 87 lines

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. 2mo ago First seen · 87 lines · 1,068 tokens per session scan A 92724cc5a1b3

Subscribe to this mod's changes

lenny_skills_plus AGENTS.md is an instructions file published in the GitHub repository liqiongyu/lenny_skills_plus (53 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,068 tokens to every session, about $0.0043 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 2026-08-30.

agent-skillsai-agentsautomationclaudecodexprompt-engineering
Related

lenny_skills_plus AGENTS.md compared with instructions from other repositories

lenny_skills_plus AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lenny_skills_plus AGENTS.mdliqiongyu/lenny_skills_plusInstructions file535mo agoApache-2.0A1,068Codex, OpenCode
ai-agent-rules-generator ui-design.instructions.mdsavedpixel/ai-agent-rules-generatorInstructions file86mo agoMITA701GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot