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 costajohnt/oss-autopilot --skill contribution-ethicsgit clone --depth 1 https://github.com/costajohnt/oss-autopilotWrote 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/costajohnt/oss-autopilot/contribution-ethics)<a href="https://agentmods.dev/skills/costajohnt/oss-autopilot/contribution-ethics"><img src="https://agentmods.dev/badge/skills/costajohnt/oss-autopilot/contribution-ethics/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/costajohnt/oss-autopilot/contribution-ethics"><img src="https://agentmods.dev/badge/skills/costajohnt/oss-autopilot/contribution-ethics.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 | $0.00647 |
| Opus 5 | $0.00035 | $0.00324 |
| Sonnet 5 | $0.00014 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
Contribution Ethics 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribution Ethics
How to behave ethically when contributing to OSS as an AI-assisted contributor: attribution, AI-tell avoidance in maintainer-visible writing, and knowing when to defer to a human.
Attribution
Do
- Attribute work properly (co-authors for human pair work)
- Give credit to human contributors in PR descriptions
- Share knowledge with other contributors
Don't
Add AI attribution to commits or PRs:
- No
Co-Authored-By: Claudetrailers - No "Generated with Claude Code" in PR descriptions
- No robot emoji attributions
- No mentions of AI assistance in comments
These rules are absolute. Contributions submitted to upstream repos must appear as solely from the human contributor unless that repo's contribution guidelines explicitly require AI disclosure.
Other related "don't"s:
- Claim credit for others' work
- Submit low-quality PRs just for contribution graphs
- Spam repos with trivial changes
AI-Tell Avoidance in Writing
AI-generated comments have recognizable patterns. Avoid these in any maintainer-visible writing (PR descriptions, review responses, issue comments):
- No changelogs in comments. "Changes in the latest commit:" with bullet points is a dead giveaway. Describe what you did in a sentence, or let the diff speak.
- Vary your openings. Don't start every response with "Thanks for the review!" or "Good catch!" Sometimes just jump to the substance.
- Match their length. If the maintainer wrote two sentences, don't respond with four paragraphs.
- Read the whole thread first. Asking about something explained three comments up is the fastest way to lose credibility.
- Mean what you say. Don't defend a position then immediately abandon it. Push back or agree — pick one.
- Figure things out yourself. If a maintainer says "add a screenshot," look at existing examples. Don't ask them to explain the tooling.
When to Defer to the Human Contributor
Some situations require the human contributor, not an AI tool:
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 · 62 lines · 70 tokens per session scan A db692ecf276c
Contribution Ethics is a skill published in the GitHub repository costajohnt/oss-autopilot (13 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 647 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
qamap-pr-qa
Local zero-LLM PR QA workflow. Use when an agent is preparing, updating, finalizing, or reviewing a pull request, asks what the PR should test, or needs commit-backed change intent, affected behavior, QA scenarios, evidence, validation commands, optional automation drafts, and manifest repair guidance.
joycraft-decompose
Break a feature brief into atomic specs — small, testable, independently executable units.
joycraft-design
Design discussion before decomposition — produce a 200-line design artifact for human review, catching wrong assumptions before they propagate into specs.
joycraft-new-feature
Guided feature development — interview the user, produce a Feature Brief, then decompose into atomic specs.
joycraft-optimize
Invoked by tune's roadmap or the human directly — semantic self-audit of harness overhead; per control it assigns a disposition (KEEP/ONEHOME/LOADLATER/MAKEACHECK/PROBATION/RETIRE) and an evidence label, advisory only.