Plan Implementation
testdouble/han
Builds a feature implementation plan from an existing feature specification (or equivalent context) through a facilitated team conversation.
Stress-test a plan before acting on it. An agent skill from chrisblattman/claudeblattman.
Install Review Plan
$ npx skills add chrisblattman/claudeblattman --skill review-plan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install chrisblattman/claudeblattman review-plan --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/chrisblattman/claudeblattman.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/starter-kit/skills/review-plan .claude/skills/review-plan && 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 "review-plan" agent skill from https://github.com/chrisblattman/claudeblattman/tree/main/plugins/starter-kit/skills/review-plan into .claude/skills/review-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan", 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/chrisblattman/claudeblattman/tree/main/plugins/starter-kit/skills/review-planType 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 chrisblattman/claudeblattman --skill review-plan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install chrisblattman/claudeblattman review-plan --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chrisblattman/claudeblattman.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/starter-kit/skills/review-plan .agents/skills/review-plan && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "review-plan" agent skill from https://github.com/chrisblattman/claudeblattman/tree/main/plugins/starter-kit/skills/review-plan into .agents/skills/review-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan", 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 chrisblattman/claudeblattman --skill review-plan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install chrisblattman/claudeblattman review-plan --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chrisblattman/claudeblattman.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/starter-kit/skills/review-plan .cursor/skills/review-plan && 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 "review-plan" agent skill from https://github.com/chrisblattman/claudeblattman/tree/main/plugins/starter-kit/skills/review-plan into .cursor/skills/review-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan", 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/chrisblattman/claudeblattman.git --path plugins/starter-kit/skills/review-plan--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 chrisblattman/claudeblattman --skill review-plan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install chrisblattman/claudeblattman review-plan --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chrisblattman/claudeblattman.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/starter-kit/skills/review-plan .gemini/skills/review-plan && 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 "review-plan" agent skill from https://github.com/chrisblattman/claudeblattman/tree/main/plugins/starter-kit/skills/review-plan into .gemini/skills/review-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan", 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 chrisblattman/claudeblattman review-planInstalls 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 chrisblattman/claudeblattman --skill review-plan -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/chrisblattman/claudeblattman.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/starter-kit/skills/review-plan .github/skills/review-plan && 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 "review-plan" agent skill from https://github.com/chrisblattman/claudeblattman/tree/main/plugins/starter-kit/skills/review-plan into .github/skills/review-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan", 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 chrisblattman/claudeblattman --skill review-plan -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install chrisblattman/claudeblattman review-plan --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chrisblattman/claudeblattman.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/starter-kit/skills/review-plan .opencode/skills/review-plan && 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 "review-plan" agent skill from https://github.com/chrisblattman/claudeblattman/tree/main/plugins/starter-kit/skills/review-plan into .opencode/skills/review-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan", 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
review-plan- GitHub stars
- 462
- Token cost
- ~1.7k tokens
- SKILL.md length
- 663 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Stress-test a plan before acting on it. An agent skill from chrisblattman/claudeblattman.
- Works in 6 steps: Find and read the plan → Pick the review path and the reviewer → Research best practices (skip when quick) → …
- Tasks that involve Planning
- SKILL.md covers Step 1 — Find and read the plan, Step 2 — Pick the review path…, Step 3 — Research best… and Step 4 — Run the critique, plus 3 more sections
- Calls gemini
What it does
Review Plan is an agent skill from chrisblattman/claudeblattman. Stress-test a plan before acting on it. Finds blind spots, missing steps, and wishful thinking, then gives a clear verdict — APPROVE, or REVISE with a fixed-up plan. Substantive plans get a council of critics by default; quick or single-pass runs one fast review instead. Use right after plan mode, or on any plan file.
Its SKILL.md is about 1.7k 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: Claude Code for academics — skills, agents, and setup guides. The licence is MIT.
When your agent uses it
- Tasks that involve Planning
- Tasks that involve Load testing
Example prompts
- “/review-plan”
Workflow steps
6 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 12e14d4. 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:
gemini
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
Review Plan loads about 1.7k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 663 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 chrisblattman/claudeblattman at commit 12e14d4, republished under its MIT licence (© chrisblattman). 663 words, ~1,701 tokens.
Download SKILL.mdSave it as
.claude/skills/review-plan/SKILL.md (or your agent's skills folder).- name
- review-plan
- description
- Stress-test a plan before acting on it. Finds blind spots, missing steps, and wishful thinking, then gives a clear verdict — APPROVE, or REVISE with a fixed-up plan. Substantive plans get a council of critics by default; `quick` or `single-pass` runs one fast review instead. Use right after plan mode, or on any plan file.
- argument-hint
- [file:path] [quick|single-pass] [role:"expert role"] [--peer codex|gemini]
/review-plan — Stress-Test a Plan
Read the plan, critique it hard, deliver a verdict. For plans of any substance the default is a small council of independent critics with a separate synthesis — three reviewers with different lenses catch more than one. quick or single-pass opts down to a single fresh-context review.
Step 1 — Find and read the plan
In priority order:
- Explicit file — the
file:pathargument. If the path doesn't exist: "File not found: [path]. Check the path and try again." - Plan-mode file — the most recent file in
~/.claude/plans/(Glob~/.claude/plans/*.md), when the user just finished plan mode. - The conversation — a plan developed or pasted in this session.
If no plan is found anywhere, reply: "No plan found. Run /review-plan right after plan mode, or /review-plan file:path/to/plan.md." and stop.
If the plan is under ~50 words, warn — "This plan is very brief; the review may be limited." — then proceed.
Step 2 — Pick the review path and the reviewer
- Council (default). Any plan where a missed flaw would cost real time, money, or credibility: implementation plans, migrations, research designs, proposals, workflow changes.
- Single-pass. Only when the user says
quickorsingle-pass, or the plan is short and low-stakes (a simple to-do sequence).
Assign an expert role for the critique — infer from the plan's content; the user's role:"..." always wins:
| The plan is about | Reviewer role |
|---|---|
| Software, automation, AI tools | AI engineering specialist |
| Grants, proposals, funders | Research funding strategist |
| Papers, studies, data analysis | Research methodology specialist |
| Project management, workflows, operations | Operations specialist |
| Anything else | Strategic planning specialist |
Announce: "Reviewing as: meticulous [role]. (Say role:\"...\" to override.)"
Step 3 — Research best practices (skip when quick)
Privacy check before any search: web search sends search terms outside Claude. If the plan includes confidential records, personal contact details, research-participant or human-subjects material, unpublished sensitive work, private financial/legal/medical/school details, or anything the user would not paste into a public website, skip web search and say: "I am skipping web search because the plan appears sensitive; reviewing from the local plan and general domain knowledge." If the plan is safe, run two web searches: "[the plan's main approach] best practices" and "[the plan's domain] common pitfalls". Distill 3–5 principles that bear on THIS plan — they feed the critique. If web search is unavailable, continue and note: "Web research unavailable; reviewing from domain knowledge."
Step 4 — Run the critique
Show full SKILL.md (270 more words)Show less
Council path (default)
Follow the bundled council skill — ${CLAUDE_PLUGIN_ROOT}/skills/council/SKILL.md — with:
- Panel: the plan panel (skeptic, pre-mortem, completeness-checker). Type: plan.
- Critic input: the full plan text plus the best-practice principles from Step 3.
--peer codex|gemini: pass it through if the user set it. The council skill checks whether that engine is actually available, asks for explicit send confirmation, and falls back to all-Claude with a friendly note if not. Privacy check first: a peer review sends the full plan to another AI service — if the plan contains confidential, personal, or research-participant material, don't pass--peer; tell the user why and run all-Claude.
The council skill owns the persona-file check, the parallel dispatch, and the mandatory separate synthesis. Don't re-implement those here.
Single-pass path (quick / single-pass / trivial plan only)
Dispatch ONE Task call, subagent_type: general-purpose — a fresh context avoids grading your own homework — with this prompt:
You are a meticulous [role]. Find what's missing, what will break, and what's
wishful thinking. Do not rationalize or hedge.
PLAN TO REVIEW: [full plan text]
BEST PRACTICES CONTEXT: [principles from Step 3, or "none — quick mode"]
Review against 6 dimensions:
1. PRE-MORTEM — it's 3 months later and this failed. Top 3 causes?
2. COMPLETENESS — what's missing that a domain expert would expect?
3. FEASIBILITY — which steps depend on unconfirmed resources, approvals, or data?
4. BEST-PRACTICE FIT — where does the plan deviate, and is the deviation justified?
5. SEQUENCING — hidden blockers? Would reordering reduce risk?
6. SPECIFICITY — could someone unfamiliar execute each step? Flag hand-waves
("figure out", "as needed") and missing success criteria.
Classify each finding: Red (will likely cause failure or major rework), Yellow
(risky but survivable), Green (minor). End with
VERDICT: APPROVE | REVISE — [one-line reason]Step 5 — Present the review
════════════════════════════════════════
PLAN REVIEW — [plan title]
════════════════════════════════════════
Reviewing as: meticulous [role] · Source: [file / plan mode / conversation]
STRENGTHS
1. [what the plan gets right — be specific]
WEAKNESSES & GAPS
🔴 [issue] → Fix: [specific change]
🟡 [issue] → Fix: [specific change]
🟢 [issue] → Fix: [specific change]
VERDICT
✅ APPROVE — [reason] or 🔄 REVISE — [reason] + revised plan belowWhen the council ran: take the verdict, blockers, and patches from the synthesis output; include the per-critic one-line verdicts; put the raw critiques in a <details> block at the bottom. If the verdict is REVISE, draft the revised plan yourself from the blockers and patches, marking changed sections [CHANGED] and additions [NEW].
Step 6 — Iterate
Ask: "Apply these revisions, or give me feedback to refine further?"
- Accept → apply the revisions to the plan file (if file-based) or present the final version.
- Feedback → loop back to Step 4 once, with the user's notes added to the critic input.
- After 2 review cycles: "This plan has been reviewed [N] times — further rounds hit diminishing returns. Consider running it and iterating in practice."
Examples
/review-plan ← right after plan mode
/review-plan file:docs/migration-plan.md
/review-plan quick
/review-plan single-pass role:"clinical trial design specialist"
/review-plan --peer codex© chrisblattman, 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 plugins/starter-kit/skills/review-plan of chrisblattman/claudeblattman.
Open the folder on GitHubat commit 12e14d4
Compare with similar skills
Review Plan 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 |
|---|---|---|---|---|---|---|
| Review Plan this skillchrisblattman/claudeblattman | 462 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Plan Implementationtestdouble/han | 281 | — | ~9.5k | Automated safety check: Pass | MIT | |
| Plan ReviewerUniClipboard/UniClipboard | 1.9k | — | ~409 | Automated safety check: Pass | AGPL-3.0 | |
| Planningmblode/agent-skills | 144 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Plan ReviewMathews-Tom/armory | 329 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT |
Similar skills
Plan Reviewer
UniClipboard/UniClipboard
Run an independent adversarial review loop for a Markdown implementation plan.
Planning
mblode/agent-skills
Creates and reviews executable implementation plans grounded in repository evidence, with vertical slices, explicit decisions, and verification criteria.
Plan Review
Mathews-Tom/armory
Pre-implementation plan audit stress-testing scope, assumptions, risks, and failure modes before code is written.
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.
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.
More from chrisblattman/claudeblattman
All 10 skills in this repoAsk Agents
chrisblattman/claudeblattman
Send a task or question to Claude Code and/or Gemini as external subagents and report back what they said.
Council
chrisblattman/claudeblattman
Dispatch a small panel of critic agents in parallel on a plan, draft, or decision, then synthesize their raw critiques in a separate fresh-context pass.
Prompt
chrisblattman/claudeblattman
Turn a rough request into a clear, structured prompt, show it, then run it.
Prompt
chrisblattman/claudeblattman
Turn a rough, dictated, or ambiguous request into a clear, structured task, then carry it out.
Review Plan
chrisblattman/claudeblattman
Review a proposed plan with a single-pass structured critique and a clear verdict.
Kit Setup
chrisblattman/claudeblattman
One-time starter-kit setup: detects optional AI engines (Codex, Gemini), confirms each with you, writes the engines config, and optionally personalizes how Claude writes for you.
Related
Categories
Questions about Review Plan
What does Review Plan do?
Stress-test a plan before acting on it. An agent skill from chrisblattman/claudeblattman. Review Plan is an agent skill from chrisblattman/claudeblattman. Stress-test a plan before acting on it.
When should I use Review Plan?
Review Plan fits situations like: tasks that involve Planning; tasks that involve Load testing.
How do I install Review Plan in Claude Code?
Run `npx skills add chrisblattman/claudeblattman --skill review-plan -a claude-code`. Or copy the skill folder (plugins/starter-kit/skills/review-plan in chrisblattman/claudeblattman) into .claude/skills/review-plan in your project. Claude Code loads it when a task matches its description.
How do I install Review Plan in Codex?
Run `npx skills add chrisblattman/claudeblattman --skill review-plan -a codex`. Or copy the skill folder (plugins/starter-kit/skills/review-plan in chrisblattman/claudeblattman) into .agents/skills/review-plan in your project. Codex loads it when a task matches its description.
Can I use Review Plan 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 chrisblattman/claudeblattman --skill review-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-plan, .gemini/skills/review-plan, .github/skills/review-plan and .opencode/skills/review-plan in your project.
What does Review Plan need to run?
Going by SKILL.md and its folder, Review Plan needs the command-line tools its instructions call (gemini).
Does Review Plan 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 Review Plan 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 Review Plan use?
Review Plan 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 Review Plan use?
About 1.7k tokens (SKILL.md is roughly 6.8k 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 Review Plan?
Skills that share tags, products or a category with Review Plan: Plan Implementation (testdouble/han, 281 stars), Plan Reviewer (UniClipboard/UniClipboard, 1.9k stars), Planning (mblode/agent-skills, 144 stars) and Plan Review (Mathews-Tom/armory, 329 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Review Plan?
chrisblattman (a GitHub user) maintains it in chrisblattman/claudeblattman, which has 462 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.
Source: chrisblattman/claudeblattman on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.