New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Plan Arbiter

by BuilderIO in BuilderIO/skills

A skill your agent uses when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed…

MITAuto-check passedDevelopment

Install Plan Arbiter

skills CLI
$ npx skills add BuilderIO/skills --skill plan-arbiter -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install BuilderIO/skills plan-arbiter --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/BuilderIO/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/plan-arbiter .claude/skills/plan-arbiter && rm -rf skills-src

Use ~/.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/

Facts

Skill name
plan-arbiter
GitHub stars
4.5k
Token cost
~1k tokens
SKILL.md length
479 words
Files
3
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed…

  • Works in 5 steps: Collect the source plans. → Normalize each plan into comparable… → Cross-review the plans against each… → …
  • Asked to compare
  • SKILL.md covers Workflow, Collect Source Plans, Normalize and Cross-Review, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Plan Arbiter is an agent skill from BuilderIO/skills. Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `README.md` and `agents/openai.yaml`).

It sits in Development, covering Pull requests and Proposals and quotes. The licence is MIT.

When your agent uses it

  • Asked to compare
  • Arbitrate competing plans from multiple agents such as Codex and Claude Code
  • More proposed plans
  • PR descriptions

Example prompts

  • “/plan-arbiter”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Collect the source plans.
  2. Normalize each plan into comparable claims.
  3. Cross-review the plans against each other and the real codebase or task
  4. Choose a winner, merge a better hybrid, or send the plans back for revision.
  5. Produce one execution handoff with verification gates and rejected

What it can do on your machine

Read from SKILL.md and the folder at commit 530d9ee. 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 (its code samples are markdown).

    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

Plan Arbiter loads about 1k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 479 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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 BuilderIO/skills at commit 530d9ee, republished under its MIT licence (© BuilderIO). 479 words, ~1,022 tokens.

Download SKILL.mdSave it as .claude/skills/plan-arbiter/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
plan-arbiter
description
Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.

Plan Arbiter

Turn competing plans into one executable direction. Preserve the best ideas, reject weak assumptions, and produce a clear handoff instead of a blended mush.

Workflow

  1. Collect the source plans.
  2. Normalize each plan into comparable claims.
  3. Cross-review the plans against each other and the real codebase or task context.
  4. Choose a winner, merge a better hybrid, or send the plans back for revision.
  5. Produce one execution handoff with verification gates and rejected alternatives.

Planning is read-only unless the user explicitly asks you to implement after the decision.

Collect Source Plans

Accept plans as pasted text, local files, session IDs, transcript paths, PRs, comments, visual-plan links, or chat history. Resolve the original artifacts when possible so you can see prompt changes and assumptions that may be missing from a final summary.

If a plan is still being written and the user asked you to wait, monitor it until it is done or blocked. If a plan cannot be resolved, continue with the available plan text and mark the missing source as a risk.

Normalize

For each plan, extract:

  • Objective and scope.
  • Key assumptions and unresolved questions.
  • Proposed files, modules, APIs, data shapes, UI states, or workflows.
  • Implementation sequence.
  • Validation strategy.
  • Rollback or migration concerns.
  • Cost, complexity, and expected executor fit.

Do not reward verbosity. Prefer plans that are concrete, grounded in real code, and honest about tradeoffs.

Show full SKILL.md (247 more words)Show less

Cross-Review

Review each plan as if another capable agent wrote it:

  • Check whether it satisfies the user's actual request.
  • Verify claims against the repo, docs, tests, screenshots, or external systems when those are relevant and available.
  • Identify hidden dependencies, missing tests, risky sequencing, vague steps, unnecessary scope, and hard-to-reverse decisions.
  • Notice complementary strengths: one plan may have the better architecture while another has the better migration or validation path.
  • Separate plan quality from executor preference. A cheaper/faster executor can be the right choice for implementation even when another model produced the best critique.

Use subagents for independent review when the plans are large, the codebase is wide, or the decision would benefit from separate technical and product passes.

Decide

Choose one of three outcomes:

  • Adopt: pick one plan mostly as written.
  • Hybrid: combine specific pieces into a stronger execution plan.
  • Revise first: request another planning pass because both plans miss a key constraint or depend on an unresolved decision.

Use this tie-break order:

  1. Correctness and fit to the user's request.
  2. Grounding in real files, APIs, tests, data, and UI behavior.
  3. Simpler first implementation that does not block the intended future.
  4. Better validation and rollback story.
  5. Lower token/time cost for execution once quality is acceptable.

Handoff

Return a compact decision memo:

md
Decision
- Adopt Plan A / Hybrid / Revise first.

Why
- The deciding evidence and tradeoffs.

Execution Plan
- Ordered steps with files or surfaces to touch.

Borrowed From Other Plans
- Useful pieces kept from non-winning plans.

Rejected
- Ideas intentionally not taking, with reasons.

Verification
- Tests, browser checks, screenshots, CI, review, or deploy checks needed.

Executor Recommendation
- Which agent/model should implement and why.

When the user already asked for execution and the chosen path is clear, proceed with the selected plan after reporting the decision briefly. Otherwise stop at the handoff and ask for approval.

© BuilderIO, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/plan-arbiter of BuilderIO/skills.

  • SKILL.md
  • README.md
  • agents/openai.yaml

Open the folder on GitHubat commit 530d9ee

Compare with similar skills

Plan Arbiter 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.

Plan Arbiter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plan Arbiter this skillBuilderIO/skills4.5k—~1kAutomated safety check: PassMIT
GitHub Voicetobihagemann/turbo406—~1.2kAutomated safety check: PassMIT
Code ReviewXRPLF/XRPL-Standards288—~825Automated safety check: PassMIT
Repo Health Sweepevloghq/evlog1.9k—~3.9kAutomated safety check: PassMIT
Deskcomm Contribuirmelgarafael/DeskcommCRM4.5k—~3.6kAutomated safety check: NotesMIT
Doesitarm App ReviewThatGuySam/doesitarm3.8k—~826Automated safety check: PassCustom licence

Similar skills

  • GitHub Voice

    tobihagemann/turbo

    Shared writing style rules for GitHub-facing output (PR comments, PR descriptions, PR titles, issues, design proposals).

    406 GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Code Review

    XRPLF/XRPL-Standards

    Review a pull request in XRPL-Standards. An agent skill from XRPLF/XRPL-Standards.

    288 GitHub stars~825 tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Repo Health Sweep

    evloghq/evlog

    Twice-weekly, coverage-led simplification audit over the whole evlog repository and Evi's real communication.

    1.9k GitHub stars~3.9k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Deskcomm Contribuir

    melgarafael/DeskcommCRM

    Guia de contribuição ao DeskcommCRM para quem vai mexer no código e abrir um pull request, sobretudo de um fork.

    4.5k GitHub stars~3.6k tokensUpdated today
    DevelopmentAuto-check: notes

  • Doesitarm App Review

    ThatGuySam/doesitarm

    Review Does It ARM app-listing pull requests and app-request or compatibility-update issues.

    3.8k GitHub stars~826 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Qv Quality Reporting

    tetherto/qvac

    Run the deterministic code-quality audit, turn related findings into contextual remediation groups, prepare approval-gated Asana proposals, reconcile recurring runs, or configure twice-monthly…

    674 GitHub stars~1.6k tokensUpdated today
    DevelopmentAuto-check passed

More from BuilderIO/skills

All 25 skills in this repo

  • Agent Watchdog

    BuilderIO/skills

    A skill your agent uses when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log…

    4.5k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Plow Ahead

    BuilderIO/skills

    A skill your agent uses when the user explicitly wants autonomous progress without routine clarification stops: "plow ahead", "do not stop", "use your best judgment", "keep going until done"…

    4.5k GitHub stars~973 tokensUpdated today
    Auto-check passed

  • Read The Damn Docs

    BuilderIO/skills

    A skill your agent uses when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs…

    4.5k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Stay Within Limits

    BuilderIO/skills

    A skill your agent uses when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window…

    4.5k GitHub stars~857 tokensUpdated today
    Auto-check passed

  • Efficient Fable

    BuilderIO/skills

    A skill your agent uses when running Claude Fable on codebase-heavy or token-heavy work and the user wants Fable to orchestrate research, coding, and testing while cheaper subagents do bounded heavy…

    4.5k GitHub stars~996 tokensUpdated today
    Auto-check passed

  • Quick Recap

    BuilderIO/skills

    A skill your agent uses when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.

    4.5k GitHub stars~352 tokensUpdated today
    Auto-check passed

Categories

Questions about Plan Arbiter

What does Plan Arbiter do?

A skill your agent uses when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed…. Plan Arbiter is an agent skill from BuilderIO/skills. Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.

When should I use Plan Arbiter?

Plan Arbiter fits situations like: asked to compare; arbitrate competing plans from multiple agents such as Codex and Claude Code; more proposed plans; PR descriptions.

How do I install Plan Arbiter in Claude Code?

Run `npx skills add BuilderIO/skills --skill plan-arbiter -a claude-code`. Or copy the skill folder (skills/plan-arbiter in BuilderIO/skills) into .claude/skills/plan-arbiter in your project. Claude Code loads it when a task matches its description.

How do I install Plan Arbiter in Codex?

Run `npx skills add BuilderIO/skills --skill plan-arbiter -a codex`. Or copy the skill folder (skills/plan-arbiter in BuilderIO/skills) into .agents/skills/plan-arbiter in your project. Codex loads it when a task matches its description.

Can I use Plan Arbiter 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 BuilderIO/skills --skill plan-arbiter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plan-arbiter, .gemini/skills/plan-arbiter, .github/skills/plan-arbiter and .opencode/skills/plan-arbiter in your project.

What does Plan Arbiter need to run?

SKILL.md names no scripts, command-line tools or credentials: Plan Arbiter is instructions for the agent only.

Does Plan Arbiter 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 Plan Arbiter 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 Plan Arbiter use?

Plan Arbiter 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 Plan Arbiter use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Plan Arbiter?

Skills that share tags, products or a category with Plan Arbiter: GitHub Voice (tobihagemann/turbo, 406 stars), Code Review (XRPLF/XRPL-Standards, 288 stars), Repo Health Sweep (evloghq/evlog, 1.9k stars) and Deskcomm Contribuir (melgarafael/DeskcommCRM, 4.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan Arbiter?

BuilderIO (a GitHub organization) maintains it in BuilderIO/skills, which has 4,528 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 7, 2026.

Source: BuilderIO/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.