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 magnus919/agent-skills --skill opensource-contributionsgit clone --depth 1 https://github.com/magnus919/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/magnus919/agent-skills/opensource-contributions)<a href="https://agentmods.dev/skills/magnus919/agent-skills/opensource-contributions"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/opensource-contributions/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/magnus919/agent-skills/opensource-contributions"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/opensource-contributions.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 | $0.00064 | $0.01315 |
| Opus 5 | $0.00032 | $0.00658 |
| Sonnet 5 | $0.00013 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
opensource-contributions 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 6d 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.
This is a copy
91% identical to opensource-contributions — 21 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Source Contributions
The Golden Rule
Make it easy for maintainers to absorb your contribution. Maintainers are often under-resourced volunteers or small teams. Every friction point you remove — unclear reproduction steps, missing tests, bad commit messages, force-pushed history — is time they don't have to spend figuring out what you did and why. The whole point is to help them, not create more work.
When to Use This Skill
- Filing a bug report or feature request on a public repository
- Preparing a pull request for any open source project
- Working on a project without documented contributing guidelines (default posture)
- Reviewing your own PR before submission
- Setting up open source conventions for your own project
Load the relevant phase reference for detailed instructions.
Quick Phase Overview
| Phase | What It Covers | Reference |
|---|---|---|
| 0a — Maintainer Conventions | README discipline, LICENSE, CONTRIBUTING.md, issue/PR templates, commit conventions, DCO, release workflow hygiene | references/phase-0a-maintainer-conventions.md |
| 0 — Before You Start | Reading CONTRIBUTING.md, checking existing issues/PRs, triaging bugfix candidates, large-change discussion etiquette | references/phase-0-before-you-start.md |
| 1 — Filing Issues | Bug report and feature request templates, agent disclosure, maintainer workflow ("issue first"), coordinated multi-issue roadmaps, multi-PR plan execution | references/phase-1-filing-issues.md |
| 2 — Pull Requests | Branching conventions, scope assessment, studying existing implementations, cross-repo comparison, commit messages, PR templates, documentation audits, CI setup | references/phase-2-pull-requests.md |
| 3 — After Submitting | CI monitoring, responding to review feedback, what to do if your PR goes stale or gets closed | references/phase-3-after-submitting.md |
| 3.5 — Follow-up After Scope Feedback | Systematic call-site audits, filing comprehensive issues, complementary PRs when maintainer scope notes identify gaps | references/phase-35-followup.md |
| 4 — Release Process | Version bumping, tagging, GitHub Releases vs tags, release workflow anatomy, handling failed releases | references/phase-4-release-process.md |
What ships with it
27 files 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.
- evals/evals.json 3.0 KB
- README.md 1.5 KB
- references/agent-checklist.md 1.6 KB
- references/ci-debugging-loop.md 9.1 KB
- references/contribution-idea-filtering.md 5.0 KB
- references/cross-fork-org-restriction.md 3.0 KB
- references/cross-fork-pr-workaround.md 2.5 KB
- references/default-posture.md 1.7 KB
- references/gh-pr-create-body-pitfall.md 1.3 KB
- references/groktocrawl-gaps-worked-example.md 3.8 KB
- references/hermes-agent-contributing-case-study.md 3.3 KB
- references/hermes-cashew-contributing-worked-example.md 4.1 KB
- references/phase-0-before-you-start.md 12 KB
- references/phase-0a-maintainer-conventions.md 11 KB
- references/phase-1-filing-issues.md 14 KB
- references/phase-2-pull-requests.md 17 KB
- references/phase-3-after-submitting.md 1.0 KB
- references/phase-35-followup.md 6.3 KB
- references/phase-4-release-process.md 4.0 KB
- references/pitfalls.md 18 KB
- references/rebase-conflict-resolution.md 4.1 KB
- references/release-workflow-completion.md 5.0 KB
- references/remote-code-exploration.md 2.9 KB
- references/sequential-pr-conflict-resolution.md 3.3 KB
- references/sleep-cycle-refactor-worked-example.md 4.5 KB
- references/tracking-upstream-fix-status.md 4.4 KB
- scripts/check-pr-template-compliance.py 3.1 KB runs code
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.
- 6d ago First seen · 102 lines · 64 tokens per session scan A e9208a53d89d
opensource-contributions is a skill published in the GitHub repository magnus919/agent-skills (75 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,315 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to opensource-contributions, differing in 21 lines, and is treated as a copy.
Other skills, from other repositories
pod-init
Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
map-diff
Analyze the impact of staged git changes against the committed Cortex function knowledge graph — shows which downstream functions are affected before you commit.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
experiment-loop
Autonomous benchmark-driven experiment loop: propose a change, measure the metric, keep what improves it, revert what doesn't, repeat. Git is the ledger — every kept improvement is a commit. Every discarded attempt is a clean revert.
commit
Read this skill before making git commits.