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 CaptainMe-AI/lead-dev-os --skill create-prgit clone --depth 1 https://github.com/CaptainMe-AI/lead-dev-osWrote 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/captainme-ai/lead-dev-os/create-pr)<a href="https://agentmods.dev/skills/captainme-ai/lead-dev-os/create-pr"><img src="https://agentmods.dev/badge/skills/captainme-ai/lead-dev-os/create-pr/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/captainme-ai/lead-dev-os/create-pr"><img src="https://agentmods.dev/badge/skills/captainme-ai/lead-dev-os/create-pr.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 | $0.00070 | $0.00911 |
| Opus 5.5 | $0.00028 | $0.00364 |
| Sonnet 5.5 | $0.00014 | $0.00182 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
create-pr 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create GitHub Pull Request Skill
Purpose
This skill creates well-structured GitHub Pull Requests with descriptive titles and bodies that communicate WHAT the changes accomplish from a product/user perspective, not HOW they were implemented. Titles and descriptions use emojis for visual clarity.
When to Use This Skill
Use this skill when:
- The user asks to create a PR or pull request
- The user wants to submit their current branch for review
- The user says "open a PR", "create a PR", "submit for review"
Process
Step 1: Gather Context
Run these commands in parallel to understand the current state:
git status— check for uncommitted changesgit log --oneline main..HEAD— see all commits on this branch vs maingit diff main...HEAD --stat— see file-level summary of all changesgit branch --show-current— get current branch name
Step 2: Analyze Changes
- Run
git diff main...HEADto read the full diff - Identify the purpose of the changes — what does this accomplish for the user/product?
- Group changes into logical themes (e.g., new feature, UI update, backend change)
- Do NOT describe implementation details (no mention of specific functions, classes, variable names, or code patterns)
Step 3: Draft the PR
Title format:
<emoji> <Short description of WHAT changed>
Title rules:
- Under 70 characters
- Start with a relevant emoji (e.g., ✨ new feature, 🐛 bug fix, 🎨 UI change, 🔧 config, 📦 dependency, 🚀 performance, 🔒 security, ♻️ refactor, 🧪 tests, 📝 docs)
- Describe WHAT, not HOW
- Use present tense ("Add dark mode" not "Added dark mode")
Body format:
## ✨ What's New
- <emoji> <Change description from user/product perspective>
- <emoji> <Change description from user/product perspective>
## 🧪 Test Plan
- [ ] <verification step>
- [ ] <verification step>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Body rules:
- Focus on WHAT changed and WHY it matters
- Use emojis for each bullet point
- Never mention file names, function names, or implementation details in the summary
- The test plan should describe how to verify the behavior, not which test files to run
- Keep bullet points concise (one line each)
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 First seen · 119 lines · 70 tokens per session scan A 71549319ccaa
create-pr is a skill published in the GitHub repository CaptainMe-AI/lead-dev-os (2 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 911 once invoked, about $0.0003 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
change-classification
Classify code changes as in-context, uncertain, or out-of-context using primary signals (branch diff, issue keywords, active tasks), secondary signals (directory proximity, test naming), and red-flag patterns (secrets, large binaries). Use when preparing commits or reviewing staged changes. This skill MUST be…
feedback-resolution
Address PR review feedback through surgical fixes traceable to specific comments, apply the Boy Scout Rule only to already-modified files (separate improve: commits), recover context by code snippet rather than line number, and enforce pushback only when factually incorrect, test-breaking, or CLAUDE.md-violating. Use…
merge-and-release
Reference document describing merge prerequisites (approval, CI checks, mergeable, conversations resolved, stale approval), release versioning (semantic semver), and changelog generation. Explains why Tier 3 confirmation is structural: merge and release cost is borne by downstream people. Reference only…
merge-conflict-resolution
Detect, classify (porcelain status; complexity: trivial, semantic, structural, delete-modify), and resolve git merge conflicts through per-file strategy selection (accept-ours, accept-theirs, manual-merge, rebase), manual conflict hunk parsing, and post-resolution verification (orphaned markers, build, tests). Use…
repo-config
Provides dynamic repository configuration patterns for gh-workflow agents. Use when an agent needs the default branch name for diffs, the repository owner/name for API calls, or branch naming and commit conventions for validation.
branch-and-task-management
Create feature branches with naming conventions, load full issue context and impact analysis, and decompose acceptance criteria into atomic parallel tasks with dependencies. Use when starting work on a GitHub issue. This skill MUST be consulted because starting code without context causes misaligned implementations…