Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Form an Agent Team of Implementer and Reviewer subagents to tackle the given task, looping implementation and review until the Reviewer reports zero high-or-above findings and no more than three mid…
Install Agent Team
$ npx skills add dyoshikawa/rulesync --skill agent-team -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dyoshikawa/rulesync agent-team --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/dyoshikawa/rulesync.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.rulesync/skills/agent-team .claude/skills/agent-team && 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 "agent-team" agent skill from https://github.com/dyoshikawa/rulesync/tree/main/.rulesync/skills/agent-team into .claude/skills/agent-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team", 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/dyoshikawa/rulesync/tree/main/.rulesync/skills/agent-teamType 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 dyoshikawa/rulesync --skill agent-team -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dyoshikawa/rulesync agent-team --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dyoshikawa/rulesync.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.rulesync/skills/agent-team .agents/skills/agent-team && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-team" agent skill from https://github.com/dyoshikawa/rulesync/tree/main/.rulesync/skills/agent-team into .agents/skills/agent-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team", 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 dyoshikawa/rulesync --skill agent-team -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dyoshikawa/rulesync agent-team --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dyoshikawa/rulesync.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.rulesync/skills/agent-team .cursor/skills/agent-team && 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 "agent-team" agent skill from https://github.com/dyoshikawa/rulesync/tree/main/.rulesync/skills/agent-team into .cursor/skills/agent-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team", 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/dyoshikawa/rulesync.git --path .rulesync/skills/agent-team--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 dyoshikawa/rulesync --skill agent-team -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dyoshikawa/rulesync agent-team --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dyoshikawa/rulesync.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.rulesync/skills/agent-team .gemini/skills/agent-team && 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 "agent-team" agent skill from https://github.com/dyoshikawa/rulesync/tree/main/.rulesync/skills/agent-team into .gemini/skills/agent-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team", 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 dyoshikawa/rulesync agent-teamInstalls 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 dyoshikawa/rulesync --skill agent-team -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dyoshikawa/rulesync.git skills-src && mkdir -p .github/skills && cp -r skills-src/.rulesync/skills/agent-team .github/skills/agent-team && 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 "agent-team" agent skill from https://github.com/dyoshikawa/rulesync/tree/main/.rulesync/skills/agent-team into .github/skills/agent-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team", 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 dyoshikawa/rulesync --skill agent-team -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dyoshikawa/rulesync agent-team --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dyoshikawa/rulesync.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.rulesync/skills/agent-team .opencode/skills/agent-team && 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 "agent-team" agent skill from https://github.com/dyoshikawa/rulesync/tree/main/.rulesync/skills/agent-team into .opencode/skills/agent-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team", 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
agent-team- GitHub stars
- 1.5k
- Token cost
- ~993 tokens
- SKILL.md length
- 533 words
- Files
- 1
- Skills in repo
- 40
- Repo updated
- First seen
- Licence
- MIT
At a glance
Form an Agent Team of Implementer and Reviewer subagents to tackle the given task, looping implementation and review until the Reviewer reports zero high-or-above findings and no more than three mid…
- Works in 3 steps: Exit Condition → Iteration Loop → Final Report
- Tasks that involve Subagents
- SKILL.md covers 0. Exit Condition, 1. Iteration Loop and 2. Final Report
- Calls pnpm
What it does
Agent Team is an agent skill from dyoshikawa/rulesync. Form an Agent Team of Implementer and Reviewer subagents to tackle the given task, looping implementation and review until the Reviewer reports zero high-or-above findings and no more than three mid findings.
Its SKILL.md is about 990 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 Agent Workflows, covering Subagents. The repository describes itself as: A Utility CLI for AI Coding Agents. The licence is MIT.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “/agent-team”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 2c577d0. 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
Shell commands in SKILL.md call:
pnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.
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
Agent Team loads about 993 tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 533 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 dyoshikawa/rulesync at commit 2c577d0, republished under its MIT licence (© dyoshikawa). 533 words, ~993 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-team/SKILL.md (or your agent's skills folder).- name
- agent-team
- description
- Form an Agent Team of Implementer and Reviewer subagents to tackle the given task, looping implementation and review until the Reviewer reports zero high-or-above findings and no more than three mid findings.
- targets
- claudecode
Agent Team
TASK = the user's request
If TASK is not provided, ask the user for the task description and stop.
Coordinate an Agent Team composed of an Implementer Agent and a Reviewer Agent. Iterate the implementation/review loop until the exit condition is satisfied.
0. Exit Condition
The loop exits when both of the following hold in a single review round:
- 0 findings of severity
highorcritical. - 3 or fewer findings of severity
mid.
Findings of severity low do not affect the exit condition.
Set a hard safety cap of 10 iterations. If the exit condition is still not met at the cap, stop the loop and report the remaining findings to the user for manual decision.
1. Iteration Loop
Repeat the following steps until the exit condition is satisfied.
1-1. Implementation Phase
Delegate to the Implementer Agent via the Agent tool.
subagent_type:general-purpose- Role framing: "You are the Implementer Agent on an Agent Team."
- Inputs to pass:
- The original TASK.
- All Reviewer findings from the previous round (if any), grouped by severity.
- Instructions to include in the prompt:
- Implement the TASK end-to-end in the current repository.
- Address every Reviewer finding from the previous round. For each finding, either fix it or, if you intentionally reject it, record the reason.
- Edit files directly; do not only describe changes.
- Run
pnpm cicheck(or the narrowerpnpm cicheck:code/cicheck:contentwhen appropriate) and fix any failures before returning. - Report: a concise summary of the changes, the list of modified files, how each previous finding was handled, and the result of the checks.
Show full SKILL.md (274 more words)Show less
1-2. Review Phase
Delegate to the Reviewer Agent via the Agent tool.
subagent_type:code-reviewer- Role framing: "You are the Reviewer Agent on an Agent Team."
- Inputs to pass:
- The original TASK.
- The Implementer's summary and the list of modified files from this round.
- Instructions to include in the prompt:
- Review the changes for correctness, design quality, tests, and adherence
to project conventions (see
CLAUDE.md,docs/**/*.md, and.claude/rules/feature-change-guidelines.md). - Also consider security concerns.
- Produce a findings list. For each finding, include:
- Sequential number (e.g.,
#1,#2). - Severity:
low/mid/high/critical. - File path and line number(s).
- Problem description and recommended fix.
- Sequential number (e.g.,
- At the end of the report, include a Severity Summary with the counts per severity level so the exit condition can be evaluated mechanically.
- Review the changes for correctness, design quality, tests, and adherence
to project conventions (see
1-3. Evaluate the Exit Condition
Parse the Reviewer's Severity Summary.
- If
high + critical == 0andmid <= 3: exit the loop. - Otherwise: feed the findings into the next Implementation Phase and continue.
Between iterations, emit a short status line to the user such as
Iteration N complete — high/critical: X, mid: Y, low: Z.
2. Final Report
After the loop exits, report the following to the user:
- Outcome:
Converged(exit condition met) orCapped(hit iteration cap). - Iterations: how many rounds were executed.
- Remaining findings: the final Severity Summary, plus the full list of
remaining
midandlowfindings (and anyhigh/criticalfindings that remain when the loop was capped). - Changes: a brief summary of what was implemented and which files were modified.
- Next steps: suggestions for the user (e.g., create a commit / PR via
the
commit-push-prskill).
Do not auto-commit or open a PR from this skill; leave that to the user.
© dyoshikawa, 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 .rulesync/skills/agent-team of dyoshikawa/rulesync.
Open the folder on GitHubat commit 2c577d0
Compare with similar skills
Agent Team 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 |
|---|---|---|---|---|---|---|
| Agent Team this skilldyoshikawa/rulesync | 1.5k | — | ~993 | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from dyoshikawa/rulesync
All 40 skills in this repoRulesync Feature Research
dyoshikawa/rulesync
Maps rulesync feature implementations to upstream coding-agent documentation.
Babysit Dependabot PR
dyoshikawa/rulesync
Babysit a Dependabot dependency-bump PR all the way to merge: verify the author is the genuine Dependabot bot, diagnose and resolve any CI failure (excluding or fixing a breaking bump when needed)…
Commit Push PR
dyoshikawa/rulesync
Commit current changes, push to remote, and create or update a pull request.
Git Worktree Runner
dyoshikawa/rulesync
Manages git worktrees using git-worktree-runner (gtr). An agent skill from dyoshikawa/rulesync.
Goal PR
dyoshikawa/rulesync
Drive a pull request to a clean state and merge it: run the review-pr skill, fix every mid-or-above finding, and repeat until no mid-or-above findings remain, then merge.
Goal Release
dyoshikawa/rulesync
Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the…
Related
Categories
Questions about Agent Team
What does Agent Team do?
Form an Agent Team of Implementer and Reviewer subagents to tackle the given task, looping implementation and review until the Reviewer reports zero high-or-above findings and no more than three mid…. Agent Team is an agent skill from dyoshikawa/rulesync. Form an Agent Team of Implementer and Reviewer subagents to tackle the given task, looping implementation and review until the Reviewer reports zero high-or-above findings and no more than three mid findings.
When should I use Agent Team?
Agent Team fits situations like: tasks that involve Subagents.
How do I install Agent Team in Claude Code?
Run `npx skills add dyoshikawa/rulesync --skill agent-team -a claude-code`. Or copy the skill folder (.rulesync/skills/agent-team in dyoshikawa/rulesync) into .claude/skills/agent-team in your project. Claude Code loads it when a task matches its description.
How do I install Agent Team in Codex?
Run `npx skills add dyoshikawa/rulesync --skill agent-team -a codex`. Or copy the skill folder (.rulesync/skills/agent-team in dyoshikawa/rulesync) into .agents/skills/agent-team in your project. Codex loads it when a task matches its description.
Can I use Agent Team 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 dyoshikawa/rulesync --skill agent-team -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-team, .gemini/skills/agent-team, .github/skills/agent-team and .opencode/skills/agent-team in your project.
What does Agent Team need to run?
Going by SKILL.md and its folder, Agent Team needs the command-line tools its instructions call (pnpm).
Does Agent Team 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 Agent Team 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 Agent Team use?
Agent Team 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 Agent Team use?
About 993 tokens (SKILL.md is roughly 4k 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 Agent Team?
Skills that share tags, products or a category with Agent Team: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Team?
dyoshikawa (a GitHub user) maintains it in dyoshikawa/rulesync, which has 1,508 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on October 9, 2026.
Source: dyoshikawa/rulesync on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.