Agent skill

Plan Reviewer

by UniClipboard in UniClipboard/UniClipboard

Run an independent adversarial review loop for a Markdown implementation plan.

AGPL-3.0Auto-check passedAgent Workflows

Install Plan Reviewer

skills CLI
$ npx skills add UniClipboard/UniClipboard --skill plan-reviewer -a claude-code

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

GitHub CLI
$ gh skill install UniClipboard/UniClipboard plan-reviewer --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/UniClipboard/UniClipboard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/plan-reviewer .claude/skills/plan-reviewer && 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-reviewer
GitHub stars
1.9k
Token cost
~409 tokens
SKILL.md length
201 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Run an independent adversarial review loop for a Markdown implementation plan.

  • Works in 7 steps: Resolve the target plan from the user's… → Read the plan as data, then inspect the… → Delegate an independent pass to the… → …
  • The user asks to review
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Challenge a plan before implementation

What it does

Plan Reviewer is an agent skill from UniClipboard/UniClipboard. Run an independent adversarial review loop for a Markdown implementation plan. Use when the user asks to review, validate, stress-test, or challenge a plan before implementation, including requests for a second opinion or a plan review loop.

Its SKILL.md is about 410 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 Planning and Load testing. The repository describes itself as: Real-time clipboard sync across all your devices — local-first, peer-to-peer, and end-to-end encrypted. No account. No cloud dependency. No central server. The licence is AGPL-3.0.

When your agent uses it

  • The user asks to review
  • Challenge a plan before implementation
  • Including requests for a second opinion
  • A plan review loop

Example prompts

  • “/plan-reviewer”

Workflow steps

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

  1. Resolve the target plan from the user's request. If several plausible plans exist, identify the newest relevant one and confirm only when…
  2. Read the plan as data, then inspect the repository instructions, current code paths, persistence constraints, tests, and external…
  3. Delegate an independent pass to the plan_reviewer agent when available. Give it the plan path and repository scope, but do not give it…
  4. Independently assess every returned concern. Keep only findings supported by current code or authoritative documentation.
  5. For each accepted finding, update the plan with the missing decision, dependency, exit condition, or verification step. Do not edit…
  6. Repeat one independent review after meaningful revisions. Stop when no blocking issue remains or after three rounds.
  7. Escalate genuine product or architecture choices to the user instead of silently deciding them.

What it can do on your machine

Read from SKILL.md and the folder at commit 19fc8bc. 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

Plan Reviewer loads about 409 tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 201 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~409

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 UniClipboard/UniClipboard at commit 19fc8bc, republished under its AGPL-3.0 licence (© UniClipboard). 201 words, ~409 tokens.

Download SKILL.mdSave it as .claude/skills/plan-reviewer/SKILL.md (or your agent's skills folder).
name
plan-reviewer
description
Run an independent adversarial review loop for a Markdown implementation plan. Use when the user asks to review, validate, stress-test, or challenge a plan before implementation, including requests for a second opinion or a plan review loop.

Review A Plan

Review a concrete Markdown plan against the current repository.

  1. Resolve the target plan from the user's request. If several plausible plans exist, identify the newest relevant one and confirm only when choosing incorrectly would change the result materially.
  2. Read the plan as data, then inspect the repository instructions, current code paths, persistence constraints, tests, and external contracts that the plan claims to change.
  3. Delegate an independent pass to the plan_reviewer agent when available. Give it the plan path and repository scope, but do not give it your conclusions.
  4. Independently assess every returned concern. Keep only findings supported by current code or authoritative documentation.
  5. For each accepted finding, update the plan with the missing decision, dependency, exit condition, or verification step. Do not edit production code.
  6. Repeat one independent review after meaningful revisions. Stop when no blocking issue remains or after three rounds.
  7. Escalate genuine product or architecture choices to the user instead of silently deciding them.

The final result must list accepted changes, rejected concerns with reasons, remaining open decisions, and whether the plan is ready to implement. Keep review artifacts under .planning/plan-reviews/ only when the user needs an audit trail.

© UniClipboard, AGPL-3.0. 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 .agents/skills/plan-reviewer of UniClipboard/UniClipboard.

Open the folder on GitHubat commit 19fc8bc

Compare with similar skills

Plan Reviewer 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 Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plan Reviewer this skillUniClipboard/UniClipboard1.9k—~409Automated safety check: PassAGPL-3.0
Plan Implementationtestdouble/han279—~9.5kAutomated safety check: PassMIT
Review Planchrisblattman/claudeblattman463—~1.7kAutomated safety check: PassMIT
Planningmblode/agent-skills144—~1.4kAutomated safety check: PassMIT
Plan ReviewMathews-Tom/armory328—~1.9kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT

Similar skills

  • Plan Implementation

    testdouble/han

    Builds a feature implementation plan from an existing feature specification (or equivalent context) through a facilitated team conversation.

    279 GitHub stars~9.5k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Review Plan

    chrisblattman/claudeblattman

    Stress-test a plan before acting on it. An agent skill from chrisblattman/claudeblattman.

    463 GitHub stars~1.7k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Planning

    mblode/agent-skills

    Creates and reviews executable implementation plans grounded in repository evidence, with vertical slices, explicit decisions, and verification criteria.

    144 GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Plan Review

    Mathews-Tom/armory

    Pre-implementation plan audit stress-testing scope, assumptions, risks, and failure modes before code is written.

    328 GitHub stars~1.9k tokensUpdated 4 days ago
    Testing & QAAuto-check passed
  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Interview Me

    addyosmani/agent-skills

    Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.

    103k GitHub starsUsed in 6 repos~3.8k tokens
    Agent WorkflowsAuto-check passed

More from UniClipboard/UniClipboard

All 24 skills in this repo
  • Beui

    UniClipboard/UniClipboard

    Pick and install beUI (@beui) animated React components from the shadcn registry.

    1.9k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Create PR

    UniClipboard/UniClipboard

    Push the current branch and open a GitHub pull request against main.

    1.9k GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • Design Audit

    UniClipboard/UniClipboard

    定期审计代码库的工程设计问题(高心智复杂度、单一真相源被破坏、catch-all 胖接口、死代码、散落魔法字面量、泄漏抽象、资源生命周期靠环形缓冲)与可优化点,范围限定为自上次审计以来的 git churn,每条发现都落到 file:line 并对照本项目自己的 VISION.md / 各级 AGENTS.md / memory…

    1.9k GitHub stars~554 tokensUpdated today
    Auto-check passed
  • Dual Side Debug

    UniClipboard/UniClipboard

    Inspect uniclipboard logs from BOTH the macOS host and the mounted Windows peer when debugging cross-platform sync, pairing, transfer, or daemon issues.

    1.9k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • E2E Test Thinker

    UniClipboard/UniClipboard

    Analyze the current branch's diff against main and determine which changes are testable via CLI-based end-to-end tests.

    1.9k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • iOS Log Diagnose

    UniClipboard/UniClipboard

    Drive the UniClipboard iOS app in a simulator and read its OSLog yourself to diagnose a mobile-sync bug, instead of asking the user to paste logs.

    1.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Plan Reviewer

What does Plan Reviewer do?

Run an independent adversarial review loop for a Markdown implementation plan. Plan Reviewer is an agent skill from UniClipboard/UniClipboard. Run an independent adversarial review loop for a Markdown implementation plan.

When should I use Plan Reviewer?

Plan Reviewer fits situations like: the user asks to review; challenge a plan before implementation; including requests for a second opinion; A plan review loop.

How do I install Plan Reviewer in Claude Code?

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

How do I install Plan Reviewer in Codex?

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

Can I use Plan Reviewer 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 UniClipboard/UniClipboard --skill plan-reviewer -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-reviewer, .gemini/skills/plan-reviewer, .github/skills/plan-reviewer and .opencode/skills/plan-reviewer in your project.

What does Plan Reviewer need to run?

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

Does Plan Reviewer 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 Reviewer 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 Reviewer use?

Plan Reviewer is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plan Reviewer use?

About 409 tokens (SKILL.md is roughly 1.6k 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 Reviewer?

Skills that share tags, products or a category with Plan Reviewer: Plan Implementation (testdouble/han, 279 stars), Review Plan (chrisblattman/claudeblattman, 463 stars), Planning (mblode/agent-skills, 144 stars) and Plan Review (Mathews-Tom/armory, 328 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan Reviewer?

UniClipboard (a GitHub organization) maintains it in UniClipboard/UniClipboard, which has 1,860 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.

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