plan-review
Review an agent's proposed work plan before execution begins.
Skill by iamthenop
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/iamthenop-plan-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/plan-review
What's inside
- Skill name
plan-review- Description
- Review an agent's proposed work plan before execution begins. Use when a builder or tester has produced a work plan from a workorder and the designer must assess it before authorizing execution. Returns one of three verdicts: execute as written, minor issues found, or stop and redraft the workorder.
- License
- MIT
- Metadata
- skill-type: deliverable · prose-setting: default
- Instructions
- 66 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- claude-code.md · references/
SKILL.md (first lines)
# Plan review A work plan is the executor's interpretation of a workorder before any change is made. Reviewing it before execution is cheaper than reviewing a pull request after. The reviewer's job is to catch misinterpretation, scope drift, and workorder defects before they become code. ## Verdicts Every plan review returns exactly one of three verdicts as its first line: **Execute as written** — the plan is complete, correctly bounded, and ready to run. No findings. **Minor issue(s) found** — the plan is executable after named corrections. Each correction is enumerated below the verdict. The executor applies every correction before starting; execution does not begin on the uncorrected plan. **Stop — redraft workorder** — the plan reveals that the workorder is ambiguous, unbounded, or requires a decision that has not been made. Execution does not begin. Findings are returned to the workorder author for a new draft. ## Review form State the verdict first. Then enumerate findings, each with: * file or workorder item reference; * the exact problem; * the required correction, verbatim where text is the deliverable. A finding is a bounded correction, not a design decision. If stating the correction requires making an architectural choice, that is a stop-and-redraft finding, not a minor issue. Do not approve a plan that expands scope beyond the workorder. Do not approve a plan that names new modules, classes, or identifiers not authorized by the workorder. Do not approve a plan that defers a required workorder field to implementation judgment. ## Stop conditions Return stop-and-redraft when: * the plan interprets an ambiguous workorder field rather than stopping on it; * the plan names work outside the allowed surface; * the plan proposes a new module, class, abstraction, or identifier not authorized by the workorder; * the plan defers a binding decision to implementation; * the plan proposes a workaround where the workorder requires a solution; * correcting the plan requires a decision the reviewer cannot make. ## Reference material * [`references/claude-code.md`](references/claude-code.md) — Claude Code plan format, stop points, and response guidance for local VS Code and cloud instances. ## Final rule A plan review authorizes execution or stops it. It does not redesign the work.
From iamthenop/infurnet-skills, MIT.
More from iamthenop/infurnet-skills
- 0.563score
purrification
iamthenop
Apply sparse feline phonetic slips to creative dialogue or monologues, using cross-language IPA similarity and salience-based spacing.
SkillAFreshness: AClaude Code +9 - 0.529score
api-docs
iamthenop
Author and structure API and interface documentation for HTTP APIs, internal RPC surfaces, and inbound webhooks.
SkillBFreshness: BClaude Code +9 - 0.529score
brand-designer
iamthenop
Author and structure brand identity documentation — brand books, style guides, logo/color/type systems, voice and slogans, and platform-specific…
SkillBFreshness: BClaude Code +9 - 0.529score
schema-design
iamthenop
Database schema design discipline — initialization strata, stratum boundaries, SQL design and comments, privileges, writers, seeds, and schema validation.
SkillBFreshness: BClaude Code +9 - 0.529score
code-comments
iamthenop
Decide whether a source comment belongs, what it may contain, and where displaced information goes instead.
SkillBFreshness: BClaude Code +9 - 0.529score
deploy-standard
iamthenop
Container build, distribution, and release promotion discipline.
SkillBFreshness: BClaude Code +9 - 0.529score
doc-comment-tags
iamthenop
Write structured documentation comments using the custom architectural tag system (@layer, @owner, @boundary, @authority, @privacy, @temporary, and related…
SkillBFreshness: BClaude Code +9 - 0.529score
java-standard
iamthenop
Java implementation rules for source layout, test placement, and documentation.
SkillBFreshness: BClaude Code +9 - 0.529score
project-bindings
iamthenop
Author and maintain the repository bindings file — the single mutable declaration of project-specific values that standards dereference.
SkillBFreshness: BClaude Code +9 - 0.526score
designer
iamthenop
Assigned Designer profile.
SkillBFreshness: BClaude Code +9 - 0.526score
prose-discipline
iamthenop
Always-required standard wherever prose is used.
SkillBFreshness: BClaude Code +9 - 0.526score
builder
iamthenop
Assigned Builder profile.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 5
- Last commit (this folder)
- Sep 3, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/iamthenop/infurnet-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from iamthenop
- 0.563score
purrification
iamthenop
Apply sparse feline phonetic slips to creative dialogue or monologues, using cross-language IPA similarity and salience-based spacing.
SkillAFreshness: AClaude Code +9 - 0.529score
code-comments
iamthenop
Decide whether a source comment belongs, what it may contain, and where displaced information goes instead.
SkillBFreshness: BClaude Code +9 - 0.529score
deploy-standard
iamthenop
Container build, distribution, and release promotion discipline.
SkillBFreshness: BClaude Code +9 - 0.529score
brand-designer
iamthenop
Author and structure brand identity documentation — brand books, style guides, logo/color/type systems, voice and slogans, and platform-specific…
SkillBFreshness: BClaude Code +9 - 0.529score
api-docs
iamthenop
Author and structure API and interface documentation for HTTP APIs, internal RPC surfaces, and inbound webhooks.
SkillBFreshness: BClaude Code +9 - 0.529score
doc-comment-tags
iamthenop
Write structured documentation comments using the custom architectural tag system (@layer, @owner, @boundary, @authority, @privacy, @temporary, and related…
SkillBFreshness: BClaude Code +9
Cite this page
plan-review skill. Agent Mart. https://agentmart.dev/skills/iamthenop-plan-review (last updated 2026-10-24)