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 kevinnft/ai-agent-skills --skill open-source-contributiongit clone --depth 1 https://github.com/kevinnft/ai-agent-skillsWrote 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/kevinnft/ai-agent-skills/open-source-contribution)<a href="https://agentmods.dev/skills/kevinnft/ai-agent-skills/open-source-contribution"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/open-source-contribution/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/kevinnft/ai-agent-skills/open-source-contribution"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/open-source-contribution.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 | $0.00017 | $0.04294 |
| Opus 5 | $0.00009 | $0.02147 |
| Sonnet 5 | $0.00003 | $0.00859 |
| Haiku 4.5 | $0.00002 | $0.00429 |
Grade A, and why
open-source-contribution 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 9d 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 — 709 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open-Source Contribution Workflow
Complete workflow for contributing high-quality PRs to open-source projects.
User Preference: Comprehensive Contributions
When user says "langsung gas dan maksimalkan" or "contribusi maksimal" or "bantu dia jadi terbaik":
- Build COMPREHENSIVE features, not minimal PRs
- Multiple related features in one PR is OK if cohesive
- Production-ready quality (tests, docs, error handling)
- Think like a 10-year veteran engineer
- Maximize impact: Analyze competitors, identify missing features, build world-class solutions
- Multi-phase approach: Quick wins first (1-2 hours), then game changers (4-5 hours)
- Quality over speed: Fix TypeScript errors immediately, don't push broken code
Pre-Contribution Analysis
1. Analyze the Project
Before forking, understand what's missing:
# Clone to analyze
git clone https://github.com/owner/repo.git
cd repo
# Check structure
ls -la
find src -name "*.tsx" | head -20
# Check existing features
grep -r "TODO\|FIXME" src/
# Check open issues/PRs
gh issue list --repo owner/repo
gh pr list --repo owner/repo
Compare with competitors:
- What do similar tools have that this doesn't?
- What are the ESSENTIAL missing features?
- What would make this project world-class?
Prioritize by impact:
- 🔥 CRITICAL: Features without which the tool is unusable (file tree, terminal, editor)
- 🎯 HIGH: Features that significantly improve UX (keyboard shortcuts, search)
- ✨ NICE: Polish and quality-of-life improvements (loading states, empty states)
2. Fork and Clone
# Fork via GitHub CLI
gh repo fork owner/repo --remote
# Or manually fork on GitHub, then:
git clone https://github.com/YOUR_USERNAME/repo.git
cd repo
git remote add upstream https://github.com/owner/repo.git
2. Star the Original Repo
Always star before contributing:
# Check if already starred
gh repo view owner/repo --json viewerHasStarred
# Star the repo
gh api --method PUT /user/starred/owner/repo
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 709 lines · 17 tokens per session scan A b3fa3f6586db
open-source-contribution is a skill published in the GitHub repository kevinnft/ai-agent-skills (14 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 4,294 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
secrets-in-git-history
Mine GitHub, GitLab and git history for identities, infrastructure and leaked credentials using commit author emails, GitHub code search, the commit .patch endpoint, trufflehog, gitleaks, git log pickaxe and full-ref history scans. Use when investigating a developer or organisation on GitHub, finding leaked API keys…
010108-version-control
Conventional commit format, git staging safety, disaster recovery with git reflog, and commit message best practices.
010109-release-automation
Semantic version mapping, semantic-release automation, post-release workflow, and release configuration for conventional commits.
datalad
Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink or a…
accessing-github-repos
GitHub repository access in containerized environments using REST API and credential detection. Use when git clone fails, or when accessing private repos/writing files via API.
opening-prs
Open a GitHub PR via API as a flowing graph — branch + push + createpr + mergeable poll, with structural protection against pushing to main/master/etc. Use when a Claude Code or Claude.ai container needs to land changes on GitHub via the API (no git CLI required) and the prose "create branch, push, open PR, wait for…