PR Review Provider
yansongda/pay
A skill your agent uses when reviewing PRs that add or modify a payment Provider in yansongda/pay - covers plugin pipeline, multi-tenant safety, signature verification, docs, and naming conventions.
How an agent watches a pull request in this repository — webhooks only, no scheduled check-ins.
Install Steward
$ npx skills add bomzheg/Shvatka --skill steward -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bomzheg/Shvatka steward --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/bomzheg/Shvatka.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/steward .claude/skills/steward && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "steward" agent skill from https://github.com/bomzheg/Shvatka/tree/master/.claude/skills/steward into .claude/skills/steward/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steward", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/bomzheg/Shvatka/tree/master/.claude/skills/stewardType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add bomzheg/Shvatka --skill steward -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bomzheg/Shvatka steward --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bomzheg/Shvatka.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/steward .agents/skills/steward && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "steward" agent skill from https://github.com/bomzheg/Shvatka/tree/master/.claude/skills/steward into .agents/skills/steward/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steward", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bomzheg/Shvatka --skill steward -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bomzheg/Shvatka steward --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bomzheg/Shvatka.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/steward .cursor/skills/steward && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "steward" agent skill from https://github.com/bomzheg/Shvatka/tree/master/.claude/skills/steward into .cursor/skills/steward/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steward", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/bomzheg/Shvatka.git --path .claude/skills/steward--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add bomzheg/Shvatka --skill steward -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bomzheg/Shvatka steward --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bomzheg/Shvatka.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/steward .gemini/skills/steward && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "steward" agent skill from https://github.com/bomzheg/Shvatka/tree/master/.claude/skills/steward into .gemini/skills/steward/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steward", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install bomzheg/Shvatka stewardInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add bomzheg/Shvatka --skill steward -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bomzheg/Shvatka.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/steward .github/skills/steward && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "steward" agent skill from https://github.com/bomzheg/Shvatka/tree/master/.claude/skills/steward into .github/skills/steward/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steward", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bomzheg/Shvatka --skill steward -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bomzheg/Shvatka steward --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bomzheg/Shvatka.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/steward .opencode/skills/steward && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "steward" agent skill from https://github.com/bomzheg/Shvatka/tree/master/.claude/skills/steward into .opencode/skills/steward/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steward", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
steward- GitHub stars
- 144
- Token cost
- ~574 tokens
- SKILL.md length
- 346 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
How an agent watches a pull request in this repository — webhooks only, no scheduled check-ins.
- Tasks that involve Pull requests
- SKILL.md covers What to do when an event does…, What not to do and What this file does not change
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Tasks that involve Webhooks
What it does
Steward is an agent skill from bomzheg/Shvatka. How an agent watches a pull request in this repository — webhooks only, no scheduled check-ins. Read before acting on a CI or review event on a PR you opened or were asked to drive.
Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Backend & APIs, covering Pull requests and Webhooks. It works with FastAPI and SQLAlchemy. The licence is MIT.
When your agent uses it
- Tasks that involve Pull requests
- Tasks that involve Webhooks
Example prompts
- “/steward”
What it can do on your machine
Read from SKILL.md and the folder at commit f2b60d6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Steward loads about 574 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 346 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from bomzheg/Shvatka at commit f2b60d6, republished under its MIT licence (© bomzheg). 346 words, ~574 tokens.
Download SKILL.mdSave it as
.claude/skills/steward/SKILL.md (or your agent's skills folder).- name
- steward
- description
- How an agent watches a pull request in this repository — webhooks only, no scheduled check-ins. Read before acting on a CI or review event on a PR you opened or were asked to drive.
Watching a pull request here
Never schedule a check-in to re-look at a PR. No send_later, no cron, no
ScheduleWakeup, no "I'll re-check in an hour". A subscribed PR delivers CI
failures, reviews and comments as webhook events; that is the whole signal, and
waiting for it costs nothing. Polling a quiet PR every hour burns a real share
of the owner's usage budget to learn that nothing changed — that has happened,
and it is why this file exists.
mcp__Claude_Code_Remote__send_later is also denied in .claude/settings.json.
The deny rule is the backstop; this file is the reason.
What to do when an event does arrive
Same posture as before, minus the timer:
- CI red on a PR you opened — root-cause it and push a fix, or establish it is not this PR's failure (red on base too, or a service the diff never touches). If it is real but out of scope, say what is failing and why you are not fixing it. Then stop; the next push produces the next event.
- A review comment — implement and push small, local asks (nits, renames, an added test, a one-function refactor). Anything larger, or anything you are unsure about, goes to the person who asked for the work — propose, don't push.
- Green check suite, your own echoed comment, a duplicate of something you already handled — nothing to do. Do not reply to say so.
What not to do
- Don't re-arm anything after handling an event.
- Don't fetch the whole PR body to learn its status;
get_check_runsand the event payload already say what changed. - Don't post "still green" or "no change" comments on the PR, and don't message the owner to report that nothing happened.
- Don't unsubscribe from the PR — the subscription is what makes the quiet waiting free.
What this file does not change
The rules your harness states as never still hold: no skipping, disabling or quarantining a test to get green; no rewriting history on someone else's branch; no empty commit or close-and-reopen to kick CI; no approving or merging. This file governs pacing, nothing else.
© bomzheg, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/steward of bomzheg/Shvatka.
Open the folder on GitHubat commit f2b60d6
Compare with similar skills
Steward next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Steward this skillbomzheg/Shvatka | 144 | — | ~574 | Automated safety check: Pass | MIT | |
| PR Review Provideryansongda/pay | 5.4k | — | ~2.4k | Automated safety check: Pass | MIT | |
| 00 Async Devai-driven-dev/framework | 513 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Forgejo CLImagnus919/agent-skills | 115 | — | ~645 | Automated safety check: Pass | MIT | |
| Fastcrudbenavlabs/fastcrud | 1.6k | — | ~5k | Automated safety check: Pass | MIT | |
| Bktavivsinai/bitbucket-cli | 233 | 1 repos | ~1k | Automated safety check: Pass | MIT |
Similar skills
00 Async Dev
ai-driven-dev/framework
Drive the async-dev pipeline from one entry point, whether setup, run, or review.
Forgejo CLI
magnus919/agent-skills
A skill your agent uses when managing a Forgejo or Gitea server from the terminal: issues, pull requests, repositories, file contents, labels, milestones, releases, webhooks, user settings, or any…
Fastcrud
benavlabs/fastcrud
A skill your agent uses when building or modifying CRUD endpoints with FastCRUD (the fastcrud PyPI package) in a FastAPI project — covers FastCRUD, crudrouter, EndpointCreator, FilterConfig…
Bkt
avivsinai/bitbucket-cli
Operate Bitbucket Cloud or Data Center repositories, pull requests, branches, issues, pipelines, permissions, and webhooks with bkt.
Phoenix Server
Arize-ai/phoenix
Backend development guide for the Phoenix AI observability platform (Strawberry GraphQL, SQLAlchemy async, FastAPI).
Related
Works with
Categories
Questions about Steward
What does Steward do?
How an agent watches a pull request in this repository — webhooks only, no scheduled check-ins. Steward is an agent skill from bomzheg/Shvatka. How an agent watches a pull request in this repository — webhooks only, no scheduled check-ins.
When should I use Steward?
Steward fits situations like: tasks that involve Pull requests; tasks that involve Webhooks.
How do I install Steward in Claude Code?
Run `npx skills add bomzheg/Shvatka --skill steward -a claude-code`. Or copy the skill folder (.claude/skills/steward in bomzheg/Shvatka) into .claude/skills/steward in your project. Claude Code loads it when a task matches its description.
How do I install Steward in Codex?
Run `npx skills add bomzheg/Shvatka --skill steward -a codex`. Or copy the skill folder (.claude/skills/steward in bomzheg/Shvatka) into .agents/skills/steward in your project. Codex loads it when a task matches its description.
Can I use Steward in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bomzheg/Shvatka --skill steward -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/steward, .gemini/skills/steward, .github/skills/steward and .opencode/skills/steward in your project.
What does Steward need to run?
SKILL.md names no scripts, command-line tools or credentials: Steward is instructions for the agent only.
Does Steward access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Steward safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Steward use?
Steward is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Steward use?
About 574 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Steward?
Skills that share tags, products or a category with Steward: PR Review Provider (yansongda/pay, 5.4k stars), 00 Async Dev (ai-driven-dev/framework, 513 stars), Forgejo CLI (magnus919/agent-skills, 115 stars) and Fastcrud (benavlabs/fastcrud, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Steward?
bomzheg (a GitHub user) maintains it in bomzheg/Shvatka, which has 144 GitHub stars. The repository was last updated on October 8, 2026.
Source: bomzheg/Shvatka on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.