Agent skill

Planning Document Review

by EveryInc in EveryInc/compound-engineering-plugin

Reviews requirements, plans and specs through role-based reviewer personas, applies proven corrections within its authority, and returns only the findings that need your call.

MITAuto-check passedAgent Workflows

Install Planning Document Review

skills CLI
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-doc-review -a claude-code

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

GitHub CLI
$ gh skill install EveryInc/compound-engineering-plugin ce-doc-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/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ce-doc-review .claude/skills/ce-doc-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/

Facts

Skill name
ce-doc-review
GitHub stars
25k
Token cost
~1.9k tokens
SKILL.md length
1,023 words
Files
27 (incl. scripts, references)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Reviews requirements, plans and specs through role-based reviewer personas, applies proven corrections within its authority, and returns only the findings that need your call.

  • Works in 2 steps: Get and Analyze Document → Announce and Dispatch Personas
  • Reviewing a requirements document before implementation starts
  • SKILL.md covers Interactive mode rules, Artifact Root, Phase 1: Get and Analyze… and Phase 2: Announce and Dispatch…, plus 1 more section
  • Calls git

What it does

The goal is a sound document that can guide the agreed work, not a longer one. The agent looks for problems that would change the outcome or materially hinder execution, and an adequate document gets no changes. Reviewer personas provide evidence, including adversarial, coherence, design, feasibility, product, scope and security lenses plus a whole-document reviewer, but the judgment stays with the agent, which checks each claim against the full document and settled decisions.

Proven errors that block an existing decision are corrected within the edit authority given. What comes back is limited to worthwhile improvements that need permission, choices or information only you can supply, and useful observations. The run is done when every selected reviewer has returned or is listed as failed, retained findings have a verified consequence, and authorized fixes are applied and checked. It reads `references/modes.md` first to handle interactive and non-interactive modes, using the host's question tool for decisions or returning structured text.

When your agent uses it

  • Reviewing a requirements document before implementation starts
  • Stress-testing a plan for feasibility, scope creep or security gaps
  • Cleaning up an existing spec without rewriting decisions already made

Example prompts

  • “Review docs/plans/billing-migration.md and fix anything that would block the agreed work.”
  • “Run a scope and feasibility review on the onboarding spec and list what needs my decision.”
  • “Check this plan non-interactively and return the findings as structured text.”

Workflow steps

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

  1. Get and Analyze Document
  2. Announce and Dispatch Personas

What it can do on your machine

Read from SKILL.md and the folder at commit 67035e9. 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

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Planning Document Review loads about 1.9k tokens when it runs, and up to ~72k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 1,023 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~72k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from EveryInc/compound-engineering-plugin at commit 67035e9, republished under its MIT licence (© EveryInc). 1,023 words, ~1,944 tokens.

Download SKILL.mdSave it as .claude/skills/ce-doc-review/SKILL.md (or your agent's skills folder). This skill also uses 26 other files; get the full folder from GitHub.
name
ce-doc-review
description
Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.
argument-hint
[mode:non-interactive] [path/to/document.{md,html}]

Document Review

Help the author finish a sound document they can use to carry out the agreed work. Find problems that would change that work's outcome or materially hinder execution, and resolve them within the authority already given. Judge the document by whether it guides correct work, not by how much detail it contains. Serious consequences warrant attention even when the defect is small. An adequate document needs no changes.

Reviewer personas supply evidence; the judgment is yours. Check their claims against the whole document, project facts, and settled decisions. Correct proven errors that prevent an existing decision from being carried out, within the edit authority and reviewer requirements the synthesis reference states. Return only worthwhile improvements still needing permission, consequential choices or essential information only the user can supply, and useful observations.

Done when: every selected reviewer has returned or is named as failed in Coverage, retained findings have a verified consequence for the agreed work, and every authorized correction assigned to Apply has been made and checked. Report that final state through the interactive approval or decision process, or return it as structured text in non-interactive mode.

Interactive mode rules

Read references/modes.md before anything else. It defines how the mode is detected, the non-interactive argument contract, and the question-tool rules: match the host's blocking question tool already in the current tool list (never call a user-facing question tool to discover it), pre-load it at the top of the interactive flow if it is listed but unloaded, and fall back to a numbered list only when the harness genuinely lacks one.

Either way, a question that calls for a user decision calls the tool or falls back loudly. Narrating it as plain text is a bug.

Artifact Root

Resolve <root> only in the no-path interactive branch, which discovers the most recent plan under <root>/plans/. Every other run reads the document at the path it was handed. So an absolute-path or non-interactive review — /tmp/plan.md, possibly outside any repo — never depends on a repo root or a CE config it does not need.

<!-- ce-docs-root:start -->

Resolve the CE artifact root <root> before composing any artifact path.

  • Read docs_root from <repo-root>/.compound-engineering/config.yaml only (<repo-root> = git rev-parse --show-toplevel). Do not read it from config.local.yaml. Unset -> <root> is docs, exactly as before.
  • Validate a set value: a repo-relative directory whose real, symlink-resolved path stays inside the repo and is neither the repo root nor under .git/. Otherwise stop with an error naming docs_root and the value -- never fall back to docs.
  • Use <root> as the sole artifact location: create it if absent, compose each path as <root>/<subdir> with this skill's own subdirectory, and never also read docs.
<!-- ce-docs-root:end -->

Phase 1: Get and Analyze Document

Read references/document-intake.md now. It covers how the document is obtained in each mode, what to do and say when no document is found, and the classification signals.

Two of its rules apply to every later step.

Verify before any dispatch. Every resolved path must be readable on disk. If one is not, dispatch no personas: reviewers read from the filesystem, so they cannot reach a path that exists only on an unchecked-out branch (issue #925).

Classify by content, not readiness labels or file path. A unified artifact with only a Product Contract is unified-requirements; missing implementation sections are expected. Any implementation planning makes it unified-plan, including incomplete or blocked planning that needs review. Other artifacts use the legacy requirements / plan split.

HTML unified artifacts take the same routes. Every fix lands in the document's native format; never insert markdown into HTML. That reference covers ID-bearing items. Pass the classification to each persona in the {document_type} slot.

Show full SKILL.md (421 more words)Show less

Phase 2: Announce and Dispatch Personas

Skip dispatch only when the completed-review reuse condition in references/document-intake.md passes; continue with that evidence at Phase 3.

Read references/persona-selection.md for each conditional persona's activation signals and the announcement format. Two of those signals over-activate on plausible evidence: the sensitive-data bound on security-lens-reviewer, and the challenge-surface bar on adversarial-document-reviewer. Then read references/dispatch.md for payload variables, slicing, model tiering, and reviewer-failure handling.

The team is coherence-reviewer and feasibility-reviewer always, plus each activated conditional persona. Announce the team with a per-persona justification before any dispatch.

Dispatch generic subagents with bounded parallelism through the platform's subagent primitive. Seed each one with the full content of its references/personas/<reviewer-name>.md. Never dispatch a standalone agent by type or name.

A capacity rejection is backpressure, not reviewer failure: wait and retry. If capacity cannot recover and selected reviewers remain undispatched, collect and clean up any started cross-model jobs as references/cross-model-review.md describes, then stop as incomplete without synthesis, fixes, or a success handoff. Preserve collected outcomes and report which reviewers completed, failed, or could not run, and why.

Cross-Model Judgment Pass

Run this pass if any of the conditional judgment trio was activated: adversarial-document-reviewer, product-lens-reviewer, security-lens-reviewer. Follow references/cross-model-review.md, which defines the whole pass: confirming the host, the one target and route used for the whole document, the disclosure before anything leaves the machine, and how peers are launched, collected, and folded in.

The pass is additive and non-blocking: a failure or timeout stops nothing and is named in Coverage. The checkout's cross_model_review_mode setting is checked first and can skip the pass with a named reason. Filter recipients only when CROSS_MODEL_PEERS is set — unset means unfiltered, not unsanctioned. Never silently change an explicit model or recipient.

Phases 3-5: Synthesis, Presentation, and Next Action

Wait until every dispatched agent has returned, including any cross-model <reviewer-name>-<provider>.json returns. Then read references/synthesis-and-presentation.md. It defines synthesis, how each finding is routed by confidence and fix class, fix application, the non-interactive result format, and the handoff to the routing question. When promoting agreement, only an artifact with independence_verified: true counts as an independent reviewer.

Interactive mode only. Read references/walkthrough.md for the grouped confirmation, the routing question, and the per-finding walk-through. Read references/bulk-preview.md for the bulk-action preview behind best-judgment routing, Append-to-Open-Questions, and auto-resolve. Load neither before review evidence is complete, whether newly collected or validly reused, and a non-interactive run never loads them at all — it stops at the structured review result.


Read only the persona prompts the current review selected. The template and schema the dispatch payload fills:

@./references/subagent-template.md

@./references/findings-schema.json

© EveryInc, 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 26 other files (scripts, references) in skills/ce-doc-review of EveryInc/compound-engineering-plugin.

  • SKILL.md
  • references/bulk-preview.md
  • references/cross-model-review.md
  • references/decision-primer.md
  • references/dispatch.md
  • references/document-intake.md
  • references/findings-schema.json
  • references/modes.md
  • references/open-questions-defer.md
  • references/persona-selection.md
  • references/personas/adversarial-document-reviewer.md
  • references/personas/coherence-reviewer.md
  • references/personas/design-lens-reviewer.md
  • references/personas/feasibility-reviewer.md
  • references/personas/product-lens-reviewer.md
  • references/personas/scope-guardian-reviewer.md
  • references/personas/security-lens-reviewer.md
  • references/personas/whole-doc-reviewer.md
  • references/rendering-floor.md
  • … and 8 more

Open the folder on GitHubat commit 67035e9

Compare with similar skills

Planning Document 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.

Planning Document Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Planning Document Review this skillEveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMIT
Interview-Driven Spec Writerposhan0126/dotclaude871—~804Automated safety check: PassMIT
Vertical-Slice Task Plannerowainlewis/blueprint412—~1.5kAutomated safety check: PassMIT
GSD Phase Discussionopen-gsd/gsd-core10k1 repos~1.5kAutomated safety check: WarnMIT
OpenSpec Guided OnboardingFission-AI/OpenSpec71k1 repos~4.5kAutomated safety check: PassMIT
Brainstorming Before BuildingjnMetaCode/superpowers-zh8.3k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Interview-Driven Spec Writer

    poshan0126/dotclaude

    Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation.

    871 GitHub stars~804 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Vertical-Slice Task Planner

    owainlewis/blueprint

    Breaks a reviewed spec into ordered, vertical-slice tasks that each fit one agent run and one pull request, grouped into milestones when useful.

    412 GitHub stars~1.5k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • GSD Phase Discussion

    open-gsd/gsd-core

    Asks adaptive questions about a project phase and records the decisions in a CONTEXT.md that later research and planning agents can act on without asking again.

    10k GitHub starsUsed in 1 repo~1.5k tokens
    Agent WorkflowsAuto-check: warnings
  • OpenSpec Guided Onboarding

    Fission-AI/OpenSpec

    Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.

    71k GitHub starsUsed in 1 repo~4.5k tokens
    Agent WorkflowsAuto-check passed
  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • GSD Plan Import

    open-gsd/gsd-core

    Ingest external plans with conflict detection against project decisions before writing anything.

    10k GitHub starsUsed in 2 repos~1k tokens
    Agent WorkflowsAuto-check: notes

More from EveryInc/compound-engineering-plugin

All 37 skills in this repo
  • Compound Learning Writer

    EveryInc/compound-engineering-plugin

    Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.

    25k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Compound Learnings Refresh

    EveryInc/compound-engineering-plugin

    Audits a repo's stored learnings against the current codebase, fixes stale, overlapping or superseded docs and reports on every document.

    25k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Compound Engineering Prototype

    EveryInc/compound-engineering-plugin

    Builds a throwaway prototype at just the fidelity needed to settle a specific how-it-should-work-or-feel question, before committing to an approach other work will treat as fixed.

    25k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Compound Engineering Setup

    EveryInc/compound-engineering-plugin

    Checks Compound Engineering plugin health and repo-local config, or scaffolds a Compound Pack when you ask for one by id.

    25k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • PR Babysitter

    EveryInc/compound-engineering-plugin

    Watches an open GitHub pull request over time, routing review comments and CI failures to other skills until the PR is ready to merge.

    25k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • CE Brainstorm

    EveryInc/compound-engineering-plugin

    Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.

    25k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Questions about Planning Document Review

What does Planning Document Review do?

Reviews requirements, plans and specs through role-based reviewer personas, applies proven corrections within its authority, and returns only the findings that need your call. The goal is a sound document that can guide the agreed work, not a longer one. The agent looks for problems that would change the outcome or materially hinder execution, and an adequate document gets no changes.

When should I use Planning Document Review?

Planning Document Review fits situations like: reviewing a requirements document before implementation starts; stress-testing a plan for feasibility, scope creep or security gaps; cleaning up an existing spec without rewriting decisions already made.

How do I install Planning Document Review in Claude Code?

Run `npx skills add EveryInc/compound-engineering-plugin --skill ce-doc-review -a claude-code`. Or copy the skill folder (skills/ce-doc-review in EveryInc/compound-engineering-plugin) into .claude/skills/ce-doc-review in your project. Claude Code loads it when a task matches its description.

How do I install Planning Document Review in Codex?

Run `npx skills add EveryInc/compound-engineering-plugin --skill ce-doc-review -a codex`. Or copy the skill folder (skills/ce-doc-review in EveryInc/compound-engineering-plugin) into .agents/skills/ce-doc-review in your project. Codex loads it when a task matches its description.

Can I use Planning Document 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 EveryInc/compound-engineering-plugin --skill ce-doc-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/ce-doc-review, .gemini/skills/ce-doc-review, .github/skills/ce-doc-review and .opencode/skills/ce-doc-review in your project.

What does Planning Document Review need to run?

Going by SKILL.md and its folder, Planning Document Review needs the command-line tools its instructions call (git).

Does Planning Document Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Planning Document 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Planning Document Review use?

Planning Document 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 Planning Document Review use?

About 1.9k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 70k tokens, read only when the agent opens those files.

What are the alternatives to Planning Document Review?

Skills that share tags, products or a category with Planning Document Review: Interview-Driven Spec Writer (poshan0126/dotclaude, 871 stars), Vertical-Slice Task Planner (owainlewis/blueprint, 412 stars), GSD Phase Discussion (open-gsd/gsd-core, 10k stars) and OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 71k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Planning Document Review?

EveryInc (a GitHub organization) maintains it in EveryInc/compound-engineering-plugin, which has 25,436 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 8, 2026.

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