Contribos

io.github.adityatiwari101104v0.2.1更新于 Oct 3, 2026

Help open-source contributors earn maintainer trust: repo rules, briefs, and pre-submit checks.

已验证STDIO仅桌面Developer ToolsKnowledge & Memory

概览

AI 生成的概览

为助手提供九个工具，用于调研开源仓库、起草贡献提案，并在提交前预检拉取请求。

功能
ContribOS 提供九个 MCP 工具（policy、brief、setup、diagnose、check、review、find、claim、tone），可读取仓库的贡献规则、AI 政策、CI 配置和过往合并记录。它会排序应阅读的文件、起草 issue 提案和评审回复、检查语气与 AI 披露尾注，并可用有改动和无改动两种方式运行测试。它本身不会创建 PR、发表评论或认领 issue。
适用场景
适合向不熟悉的仓库提交拉取请求的贡献者，或需要仓库专属规则与提交前检查的编码助手。当你想要有证据支撑的文件定位、过往 PR 先例，以及在维护者看到之前先审阅你的说明时，它很有用。
运行要求
通过 pip 安装的本地 Python 3.10+ 包，以及 git。find、从 issue URL 使用 claim 或 brief、review 和 record 需要 GITHUB_TOKEN。可选的 AI 摘要使用 CONTRIBOS_LLM 配合 ANTHROPIC_API_KEY 或 OPENAI_API_KEY，以及 CONTRIBOS_MODEL。缓存位于 ~/.cache/contribos，可通过 CONTRIBOS_CACHE 配置。
安装前请注意
GITHUB_TOKEN 会授予对你 GitHub 账户的访问权限，请谨慎限定其范围。设置 CONTRIBOS_LLM 后，可选的 AI 摘要会把已收集的证据发送给 Anthropic 或 OpenAI。该工具会写入本地文件，如 SKILL.md、钩子和 HTML 记录，并把仓库克隆到缓存中。它不会创建 PR 或发表评论，这些操作仍由你完成。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Contribos，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

ContribOS

[PyPI version] [Downloads] [License: MIT] [Python versions] [Dependencies]

Get trusted. Get merged. Come back. ContribOS helps new open-source contributors earn trust. It finds where you're welcome, shows how this repo wants the change done, checks that you truly understand your change, coaches you through review, and turns merged PRs into a record the next maintainer can verify.

In 2026, writing code is not the hard part of contributing. AI made PRs cheap, maintainers answered with PR caps, vouch lists and AI policies, and newcomer merge rates fell. ContribOS makes your PR worth a maintainer's time.

ContribOS never opens PRs, posts comments or claims issues for you, and it never writes your explanation. It points, and you decide.

The journey

StepCommandWhat you get
Findcontribos find --lang python --topic webOpen issues sorted into Good bet / Possible / Skip, each with evidence: claimed? open PR? maintainer active? clear? Plus repo welcome: archived, vouch list, AI policy, outside-PR merge rate, how long outside PRs wait for a first human reply, how many stall, a stale bot, and your own open PRs there
Rulescontribos policy owner/repoThe repo's AI policy, disclosure format (Assisted-by: and similar trailers), vouch gate, "no AI on good first issues", issue-first and claim-first norms, tests, changelog, DCO/CLA, style tools and activity, each quoted with file:line. --json gives the same rules in a form agents can read
Proposecontribos claim <issue-url>A short proposal to post before coding: likely files, a similar-size past PR, where the test goes, and one real question. Warns about taken issues, no maintainer yet, good-first-issue AI rules and issue-first rules. If the repo has a vouch list, it drafts the introduction first
Tonecontribos tone comment.md --kind commentFlags machine-written tells (delve, buzzwords, assistant openers, filler), length, a missing question and leftover placeholders in anything you're about to post
Agent rulescontribos agent-rules . --ai "Claude Code"Teaches your coding agent this repo's rules: a SKILL.md for Claude Code, Codex, Copilot and Cursor, a hook that stops the agent opening PRs or posting comments, and a commit-msg hook for sign-off and the AI-disclosure trailer. All local-only, excluded from git
Setupcontribos setup owner/repoExact steps taken from the repo's CI and contributing guide: runtime version, install, services, env vars, test and lint commands
Diagnosecontribos setup --diagnose output.txtWhat a failure means: missing dependency, wrong version, service down, env var, native build tools, flaky test, or a real test failure (and how to check it isn't yours)
Understandcontribos brief <issue-url>Files to read with the reasons each was picked, similar past PRs and what reviewers said, related tests, look-alike files to leave alone, house rules, and likely review questions. Add --llm for a plain-words summary that is grounded in the evidence
Provecontribos check --explain explain.md --verify-test "pytest tests/test_x.py" --issue 123 --ai "Claude Code: drafted the test" --pr-draft pr.mdPre-submit review: scope versus similar past changes, tests, changelog, sign-off, debug leftovers, AI policy and disclosure trailers, competing PRs for the same issue. --verify-test runs your test with the fix and again with your source files swapped back to the base version, so you can show it fails without your change. It checks that your explanation covers every changed file and states what you're unsure of, then drafts the PR: what and why, how you verified it, what you're unsure about, related past changes, AI assistance
Respondcontribos review <pr-url> --path .Each reviewer comment classified (blocking, change, question, nit…), the code it points at, the house rule it echoes, a reply draft, what's still unanswered and for how long, and failing CI
Growcontribos record <github-user> --html me.htmlA public, linkable record: merged PRs, change requests, whether you answered every review comment, whether you explained your change and disclosed AI use
Agentscontribos mcpNine MCP tools for Claude Code, Cursor, Codex and others (policy, brief, setup, diagnose, check, review, find, claim, tone), taking text as input where an agent has text: claude mcp add contribos -- python -m contribos mcp

Install

sh
pip install contribos     # Python 3.10+, git. Zero external dependencies.export GITHUB_TOKEN=...   # needed for find, claim/brief from an issue URL, review, record

Everything that can run offline does: policy, brief --title, claim --title, setup, check, bench and review --data need only git. Add --offline to skip the API, and --update to fetch new commits. Clones and indexes are cached in ~/.cache/contribos (CONTRIBOS_CACHE).

Optional AI summaries: CONTRIBOS_LLM=anthropic (with ANTHROPIC_API_KEY) or CONTRIBOS_LLM=openai (with OPENAI_API_KEY), plus optional CONTRIBOS_MODEL. The model only explains evidence ContribOS already gathered. Any sentence citing a file outside that evidence is dropped.

How it works

  • repo.py handles cached clones. It reads any revision with git show and git grep, so no checkout is needed.
  • precedent.py builds a SQLite index of main-line changes (squash and merge PRs), the files they touched, and the issues they fixed.
  • policy.py is the policy radar, built from contribution docs, AI policies, templates, vouch lists, CI config and history.
  • brief.py ranks files by rare-term matches in code, path matches, and files touched by similar past PRs. It also finds related tests via co-change history.
  • check.py is the pre-submit check, the proof-of-understanding check and the PR draft.
  • setup_doctor.py produces setup steps from CI and docs, and diagnoses failures.
  • find.py checks issue takeability, repo welcome and responsiveness.
  • claim.py drafts the proposal and vouch introduction.
  • proof.py runs a test with and without your change (files restored in finally).
  • tone.py checks text you're about to post.
  • agent_rules.py writes the local agent skill and hooks.
  • review.py classifies review comments, drafts replies and tracks follow-through.
  • record.py builds the contribution record (markdown plus a self-contained HTML page).
  • llm.py is the optional provider layer (Anthropic or OpenAI) with citation grounding.
  • mcp_server.py is a dependency-free MCP stdio server.
  • github.py is the optional API client. Every caller handles its absence.
  • bench.py runs the history benchmark.

Benchmark (2026-09-28, offline, PR titles standing in for issues)

RepoBrief hit@5Grep-only hit@5
pallets/flask (30 PRs)0.770.73
pytest-dev/pytest (30 PRs)0.870.87

Matching against past PRs barely improves file finding, which supports the plan's bet that finding files is a commodity. The value is in how past PRs did it and what reviewers asked. The next benchmark needs real issue text and review comments, which requires GITHUB_TOKEN.

Status

  • Tested on real repos (Flask, pytest, Ghostty): policy, brief, claim --title, setup, check, bench, mcp.
  • Tested against the live GitHub API on 2026-10-01: find (scored issue takeability and maintainer response medians on maximilianfeix/proxy-scraper and brekkylab/backlot), claim <url> (drafted pre-coding proposals with past similar PRs and file targets), and record (verified public merged PR portfolio for @adityatiwari101104).
  • Tested on temporary git repos: agent-rules (git status stays clean, the guard blocks gh pr create, the commit-msg hook enforces sign-off and the trailer), check --verify-test, tone, policy radar v2.
  • Tests: python -m unittest discover -s tests (40 tests, CI matrix on Linux, macOS, and Windows).

Releasing

To publish a new release to PyPI:

sh
python -m buildtwine upload dist/*git tag v<version>git push origin v<version>

来源：README.md，提交 9ddb5f4

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v0.2.1最新Oct 3, 2026