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 the-open-agent/oss-skills --skill contributor-experiencegit clone --depth 1 https://github.com/the-open-agent/oss-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/the-open-agent/oss-skills/contributor-experience)<a href="https://agentmods.dev/skills/the-open-agent/oss-skills/contributor-experience"><img src="https://agentmods.dev/badge/skills/the-open-agent/oss-skills/contributor-experience/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/the-open-agent/oss-skills/contributor-experience"><img src="https://agentmods.dev/badge/skills/the-open-agent/oss-skills/contributor-experience.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 | $0.00101 | $0.02088 |
| Opus 5 | $0.00051 | $0.01044 |
| Sonnet 5 | $0.00020 | $0.00418 |
| Haiku 4.5 | $0.00010 | $0.00209 |
Grade A, and why
contributor-experience 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributor Experience
Contributors are not recruited; they are unblocked. Almost everyone who could contribute to your project already wanted to at some point and hit a wall. Find the wall.
The funnel
Each step loses most of the people at the previous one. Fix the leakiest step, not your favorite one.
Uses the project 1000
Hits a bug/limitation 200
Considers fixing it 50 ← lost to: no clear entry point, unclear scope
Clones and sets up 20 ← lost to: setup fails on their machine ★ biggest leak
Makes the change 8 ← lost to: can't find where, tests fail confusingly
Opens a PR 5 ← lost to: process anxiety, CLA friction
Gets it merged 3 ← lost to: slow review, endless nits
Contributes again 1 ← lost to: no acknowledgment
The largest single leak in most projects is setup. It is also the cheapest to fix and the least glamorous, which is why it stays broken.
Setup that works on the first try
Target: git clone → working dev environment → passing tests, in under 10 minutes,
with one command, on macOS, Linux, and Windows.
git clone https://github.com/owner/repo && cd repo
make setup # installs deps, sets up hooks, seeds fixtures
make test # passes
Verify it the only way that works: on a clean machine, or better, a container. Your laptop has fifteen things installed that you have forgotten about.
docker run --rm -it -v "$PWD:/w" -w /w node:22 sh -c 'make setup && make test'
Better still, ship a devcontainer (.devcontainer/devcontainer.json) or a Nix flake so
"works on my machine" stops being a category of problem. GitHub Codespaces then gives
contributors a zero-install path, which converts drive-by fixers who will never
configure a local toolchain for a one-line change.
Windows deserves explicit attention: it is where setup silently fails and where you
will never see the person who gave up. Test it, or say clearly in CONTRIBUTING.md
that WSL is required.
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 · 201 lines · 101 tokens per session scan A d937149899d1
contributor-experience is a skill published in the GitHub repository the-open-agent/oss-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 2,088 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
jira-server-pat-cli
A command-line workflow for managing self-hosted Jira Server or Jira Data Center through Jira's REST API. Jira is a system for tracking issues, projects, work, and software tasks.
issue-comment
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.
github-issues
GitHub issue'larını gh veya REST ile oluştur, sırala, etiketle, ata.
phase-closeout
A Chinese-language stage closer that summarizes completed work, records decisions, updates project status, and prepares the next conversation.
handoff
Use when leaving a project, joining a project, or performing any project/module handover. Detects .handoff/ directory presence but always confirms intent before acting.