Agent skill

Plan Review

Reviews and adjusts PRD plans based on research findings. An agent skill from YougLin-dev/Aha-Loop.

MITAuto-check passedProduct & Project Management

Install Plan Review

skills CLI

$ npx skills add YougLin-dev/Aha-Loop --skill plan-review -a claude-code

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

GitHub CLI

$ gh skill install YougLin-dev/Aha-Loop plan-review --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/YougLin-dev/Aha-Loop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/plan-review .claude/skills/plan-review && 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/

Paste into Claude Code

Install the "plan-review" agent skill from https://github.com/YougLin-dev/Aha-Loop/tree/main/.agents/skills/plan-review into .claude/skills/plan-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-review", 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

$skill-installer install https://github.com/YougLin-dev/Aha-Loop/tree/main/.agents/skills/plan-review

Type 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.

skills CLI

$ npx skills add YougLin-dev/Aha-Loop --skill plan-review -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install YougLin-dev/Aha-Loop plan-review --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/plan-review .agents/skills/plan-review && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "plan-review" agent skill from https://github.com/YougLin-dev/Aha-Loop/tree/main/.agents/skills/plan-review into .agents/skills/plan-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-review", 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.

skills CLI

$ npx skills add YougLin-dev/Aha-Loop --skill plan-review -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install YougLin-dev/Aha-Loop plan-review --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/plan-review .cursor/skills/plan-review && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "plan-review" agent skill from https://github.com/YougLin-dev/Aha-Loop/tree/main/.agents/skills/plan-review into .cursor/skills/plan-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-review", 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

$ gemini skills install https://github.com/YougLin-dev/Aha-Loop.git --path .agents/skills/plan-review

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add YougLin-dev/Aha-Loop --skill plan-review -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install YougLin-dev/Aha-Loop plan-review --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/plan-review .gemini/skills/plan-review && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "plan-review" agent skill from https://github.com/YougLin-dev/Aha-Loop/tree/main/.agents/skills/plan-review into .gemini/skills/plan-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-review", 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.

GitHub CLI

$ gh skill install YougLin-dev/Aha-Loop plan-review

Installs 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).

skills CLI

$ npx skills add YougLin-dev/Aha-Loop --skill plan-review -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/plan-review .github/skills/plan-review && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "plan-review" agent skill from https://github.com/YougLin-dev/Aha-Loop/tree/main/.agents/skills/plan-review into .github/skills/plan-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-review", 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.

skills CLI

$ npx skills add YougLin-dev/Aha-Loop --skill plan-review -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install YougLin-dev/Aha-Loop plan-review --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/plan-review .opencode/skills/plan-review && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "plan-review" agent skill from https://github.com/YougLin-dev/Aha-Loop/tree/main/.agents/skills/plan-review into .opencode/skills/plan-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-review", 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: plan-review
GitHub stars: 181
Token cost: ~1.8k tokens
SKILL.md length: 546 words
Files: 1
Skills in repo: 15
Repo updated: Feb 3, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Reviews and adjusts PRD plans based on research findings. An agent skill from YougLin-dev/Aha-Loop.

Works in 10 steps: Modify Existing Story → Add New Story → Split Story → …
Update prd based on research
SKILL.md covers The Job, When to Modify the Plan, Types of Plan Modifications and Plan Review Process, plus 4 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Plan Review is an agent skill from YougLin-dev/Aha-Loop. Reviews and adjusts PRD plans based on research findings. Use after completing research to evaluate story modifications. Triggers on: review plan, adjust stories, update prd based on research.

Its SKILL.md is about 1.8k 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 Product & Project Management, covering PRD writing. The repository describes itself as: [MVP] Aha Loop is a fully autonomous AI development system, extended from the core ideas of Ralph. It's not just an execution engine, but a complete AI development framework with… The licence is MIT.

When your agent uses it

Update prd based on research
Tasks that involve PRD writing

Example prompts

“Use the plan-review skill to review and adjusts PRD plans based on research findings. An agent skill from YougLin-dev/Aha-Loop”
“/plan-review”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

Modify Existing Story
Add New Story
Split Story
Reorder Stories
Remove Story
Read Research Report
Evaluate Impact
Draft Changes
Update prd.json
Normalize Priorities

What it can do on your machine

Read from SKILL.md and the folder at commit 8d799b2. 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 json, javascript and 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 Review loads about 1.8k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 546 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~51
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

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 YougLin-dev/Aha-Loop at commit 8d799b2, republished under its MIT licence (© YougLin-dev). 546 words, ~1,812 tokens.

Download SKILL.mdSave it as .claude/skills/plan-review/SKILL.md (or your agent's skills folder).

name: plan-review
description: Reviews and adjusts PRD plans based on research findings. Use after completing research to evaluate story modifications. Triggers on: review plan, adjust stories, update prd based on research.

Plan Review Skill

Evaluate research findings and decide whether to adjust upcoming stories in the PRD.

The Job

Read the research report for the current story
Evaluate if findings impact the current or future stories
Decide on plan modifications (if any)
Update prd.json with changes
Document all changes in changeLog
Ensure plan remains coherent and achievable

When to Modify the Plan

MODIFY stories when research reveals:

A better technical approach than originally planned
Missing prerequisite steps
Stories that should be split (too large for one context)
Stories that can be combined (too small, tightly coupled)
Changed dependencies requiring reordering
New edge cases requiring additional acceptance criteria

DO NOT modify when:

The finding is interesting but doesn't affect implementation
Changes would invalidate already-completed stories
The modification is scope creep (outside original PRD goals)

Types of Plan Modifications

1. Modify Existing Story

Update acceptance criteria, description, or research topics.

json

{
  "timestamp": "2026-01-29T12:00:00Z",
  "storyId": "US-002",
  "action": "modified",
  "reason": "Research found that existing badge component supports priority colors, simplifying implementation",
  "changes": {
    "acceptanceCriteria": {
      "removed": ["Create new PriorityBadge component"],
      "added": ["Reuse Badge component with priority color variant"]
    }
  }
}

2. Add New Story

Insert a prerequisite or follow-up story.

json

{
  "timestamp": "2026-01-29T12:00:00Z",
  "storyId": "US-001.5",
  "action": "added",
  "reason": "Research revealed need for database index on priority column for filter performance",
  "insertAfter": "US-001"
}

3. Split Story

Break a story into smaller pieces.

json

{
  "timestamp": "2026-01-29T12:00:00Z",
  "storyId": "US-003",
  "action": "split",
  "reason": "Story too large - separating dropdown component from save logic",
  "splitInto": ["US-003a", "US-003b"]
}

4. Reorder Stories

Change priority/order based on new dependencies.

json

{
  "timestamp": "2026-01-29T12:00:00Z",
  "storyId": "US-004",
  "action": "reordered",
  "reason": "URL state management needed before filter implementation",
  "newPriority": 2,
  "previousPriority": 4
}

5. Remove Story

Mark a story as unnecessary (cannot remove completed stories).

json

{
  "timestamp": "2026-01-29T12:00:00Z",
  "storyId": "US-005",
  "action": "removed",
  "reason": "Research found this functionality already exists in the codebase"
}

Plan Review Process

Step 1: Read Research Report

Load the research report from scripts/aha-loop/research/[story-id]-research.md

Focus on:

Implementation recommendations
Alternatives comparison (if recommendation differs from plan)
Follow-up research needs
Gotchas discovered

Step 2: Evaluate Impact

For each finding, ask:

Does this affect the current story?
- Update acceptance criteria if needed
- Add implementation notes
Does this affect future stories?
- Check if dependencies changed
- Check if new prerequisites needed
- Check if any stories can be simplified/removed
Does this reveal scope issues?
- Story too big? Split it.
- Story too small? Combine with related story.
- Missing stories? Add them.

Step 3: Draft Changes

Before modifying prd.json:

List all proposed changes
Verify no completed stories are affected
Ensure changes maintain logical story order
Check that all stories remain achievable in one context window

Show full SKILL.md (219 more words)Show less

Step 4: Update prd.json

Backup first (automatic via aha-loop.sh, but verify).

Apply changes to prd.json:

javascript

// Example: Adding a story
{
  "id": "US-001.5",
  "title": "Add database index for priority filtering",
  "description": "As a developer, I need an index on priority column for efficient filtering.",
  "acceptanceCriteria": [
    "Create index on tasks.priority column",
    "Migration runs without errors",
    "Typecheck passes"
  ],
  "priority": 1.5,  // Will be normalized later
  "passes": false,
  "researchTopics": [],
  "researchCompleted": true,  // No research needed for simple index
  "learnings": "",
  "implementationNotes": "Discovered during US-001 research that filter queries will need this index",
  "notes": ""
}

Add to changeLog:

javascript

{
  "changeLog": [
    // ... existing entries
    {
      "timestamp": "2026-01-29T12:00:00Z",
      "storyId": "US-001.5",
      "action": "added",
      "reason": "Research for US-001 revealed need for index to support efficient priority filtering (US-004)",
      "researchSource": "scripts/aha-loop/research/US-001-research.md"
    }
  ]
}

Step 5: Normalize Priorities

After modifications, ensure priorities are sequential:

javascript

// Before: [1, 1.5, 2, 3, 4]
// After:  [1, 2, 3, 4, 5]

Safety Rules

NEVER:

Delete or modify stories where passes: true
Add scope beyond original PRD goals
Create circular dependencies between stories
Make changes without documenting in changeLog

ALWAYS:

Document the reason for every change
Reference the research source
Maintain dependency order (schema → backend → UI)
Keep stories small enough for one context window

Review Report Template

After plan review, append to progress.txt:

markdown

## Plan Review - [Date/Time]

### Research Analyzed
- [Story ID]: [Research report path]

### Changes Made

**[Action Type]: [Story ID]**
- Reason: [Why this change was needed]
- Impact: [What this affects]

### No Changes Made (If Applicable)
- Research findings do not require plan modifications
- Reason: [Why no changes needed]

### Updated Story Order
1. US-001: [Title] ✓ (completed)
2. US-001.5: [Title] (new)
3. US-002: [Title]
...

---

Example: Complete Plan Review

Scenario: Research for US-001 (Add priority to database) revealed:

An index is needed for filter performance
The existing Badge component can be reused
URL state management patterns already exist in codebase

Changes:

Add US-001.5 - Create index on priority column
- Reason: Filter queries (US-004) will be slow without index
Modify US-002 - Update acceptance criteria
- Remove: "Create PriorityBadge component"
- Add: "Reuse Badge component with 'priority' variant prop"
Modify US-004 - Add implementation note
- Note: "Use existing useUrlState hook from src/hooks/"

No reordering needed - dependencies unchanged.

Checklist

Before completing plan review:

Research report fully analyzed
All impacted stories identified
No completed stories modified
Changes documented in changeLog
Priorities normalized
Dependencies still valid
All stories achievable in one context window
Review summary added to progress.txt

Files

Just SKILL.md in .agents/skills/plan-review of YougLin-dev/Aha-Loop.

Open the folder on GitHubat commit 8d799b2

Compare with similar skills

Plan Review 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 Review compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Plan Review this skillYougLin-dev/Aha-Loop	181	—	~1.8k	Automated safety check: Pass	MIT	8 mo ago
CCPM Project Managementautomazeio/ccpm	8.4k	—	~1.1k	Automated safety check: Pass	MIT	6 mo ago
Ralph Tui Create Beadssubsy/ralph-tui	2.5k	1 repos	~2.6k	Automated safety check: Pass	MIT	1 mo ago
Trellis Brainstormanjiemo/SunnyBeach	178	7 repos	~4k	Automated safety check: Pass	Apache-2.0	27 days ago
Adversarial Speczscole/adversarial-spec	556	1 repos	~8.3k	Automated safety check: Notes	MIT	8 mo ago
Ralph Tui Create Beads Rustsubsy/ralph-tui	2.5k	1 repos	~2.8k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

CCPM Project Management
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
Product & Project ManagementAuto-check passed
Ralph Tui Create Beads
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
2.5k GitHub starsUsed in 1 repo~2.6k tokens
Product & Project ManagementAuto-check passed
Trellis Brainstorm
anjiemo/SunnyBeach
Guides collaborative requirements discovery before implementation.
178 GitHub starsUsed in 7 repos~4k tokens
Product & Project ManagementAuto-check passed
Adversarial Spec
zscole/adversarial-spec
Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.
556 GitHub starsUsed in 1 repo~8.3k tokens
Product & Project ManagementAuto-check: notes
Ralph Tui Create Beads Rust
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).
2.5k GitHub starsUsed in 1 repo~2.8k tokens
Product & Project ManagementAuto-check passed
Ouroboros PM Interview
Q00/ouroboros
Runs a guided product-manager interview that classifies each question automatically and produces a Product Requirements Document.
6.2k GitHub starsUsed in 1 repo~5.7k tokens
Product & Project ManagementAuto-check passed

Questions about Plan Review

What does Plan Review do?

Reviews and adjusts PRD plans based on research findings. An agent skill from YougLin-dev/Aha-Loop. Plan Review is an agent skill from YougLin-dev/Aha-Loop. Reviews and adjusts PRD plans based on research findings.

When should I use Plan Review?

Plan Review fits situations like: update prd based on research; tasks that involve PRD writing.

How do I install Plan Review in Claude Code?

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

How do I install Plan Review in Codex?

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

Can I use Plan Review 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 YougLin-dev/Aha-Loop --skill plan-review -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-review, .gemini/skills/plan-review, .github/skills/plan-review and .opencode/skills/plan-review in your project.

What does Plan Review need to run?

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

Does Plan Review 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 Review 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 Review use?

Plan Review 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 Review use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 Review?

Skills that share tags, products or a category with Plan Review: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Adversarial Spec (zscole/adversarial-spec, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan Review?

YougLin-dev (a GitHub user) maintains it in YougLin-dev/Aha-Loop, which has 181 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on February 3, 2026.

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

Install Plan Review

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Plan Review Skill

The Job

When to Modify the Plan

Types of Plan Modifications

1. Modify Existing Story

2. Add New Story

3. Split Story

4. Reorder Stories

5. Remove Story

Plan Review Process

Step 1: Read Research Report

Step 2: Evaluate Impact

Step 3: Draft Changes

Step 4: Update prd.json

Step 5: Normalize Priorities

Safety Rules

NEVER:

ALWAYS:

Review Report Template

Example: Complete Plan Review

Checklist

Files

Compare with similar skills

Similar skills

More from YougLin-dev/Aha-Loop

Related

Questions about Plan Review