review-plan-team-mode

review-plan-team-mode is a skill for Claude Code, Codex from 85danf/agent-skills. It costs 95 tokens per session (1,407 once invoked), scanned A, original, MIT.

A review process that compares implementation plans with the design or brainstorming documents they came from. It classifies the documents, maps them together, and uses parallel reviewers to check whether the plan is complete and aligned.

In plain words
What is it for?
Use it to validate one or more implementation plans against their source designs, specifications, or requirements. It checks that the plan includes the intended decisions, tasks, and pseudocode.
Why use it?
It catches missing requirements, incorrect interpretations, and implementation steps that do not match the agreed design before work begins. It also requires clarification when the document types or mapping are unclear.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to validate one or more implementation plans against their source designs, specifications, or requirements. It checks that the plan includes the intended decisions, tasks, and pseudocode.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/85danf/agent-skills/review-plan-team-mode
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add 85danf/agent-skills --skill review-plan-team-mode
Clone the repo
git clone --depth 1 https://github.com/85danf/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-plan-team-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/85danf/agent-skills/review-plan-team-mode/github.svg)](https://agentmods.dev/skills/85danf/agent-skills/review-plan-team-mode)
Your own site
<a href="https://agentmods.dev/skills/85danf/agent-skills/review-plan-team-mode"><img src="https://agentmods.dev/badge/skills/85danf/agent-skills/review-plan-team-mode/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-plan-team-mode

Your own site · 80×15
<a href="https://agentmods.dev/skills/85danf/agent-skills/review-plan-team-mode"><img src="https://agentmods.dev/badge/skills/85danf/agent-skills/review-plan-team-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,407 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.01407
Opus 5 $0.00048 $0.00704
Sonnet 5 $0.00019 $0.00281
Haiku 4.5 $0.00010 $0.00141

Measured 9d ago against content hash 706e0ee8af90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-plan-team-mode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude/skills/review-plan-team-mode/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewing Plan Against Design

Verify that implementation plans are correctly derived from their source design documents using a team of parallel reviewer agents.

Prerequisite: Requires experimental agent teams. Enable CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS in settings.json or environment.

Workflow

Step 1: Classify Input Files

Examine every @-referenced file. Classify each as design or plan:

Signal Design doc Plan doc
Filename contains architecture, design, brainstorm, spec, rfc, requirements plan, implementation, task, phase, batch
Content structure Goals, principles, decisions, tradeoffs, diagrams Steps, tasks, acceptance criteria, pseudocode, file paths
Tone "We should...", "The system will...", "Key decision:" "Create file X", "Add method Y", "Step 1: implement..."

If classification is ambiguous for any file, ask the user. Do not guess.

Step 2: Determine Mapping Strategy

Scenario Strategy
1 design + 1 plan Direct. One review pair.
1 design + N plans Auto-map all plans to the single design. N pairs.
N designs + M plans Ask the user to map them explicitly.

For N:M, prompt the user:

I found multiple design and plan docs. Which design verifies which plan(s)?

Design docs: design-auth.md, design-api.md
Plan docs: plan-auth.md, plan-api.md, plan-integration.md

Example: "design-auth -> plan-auth, design-api -> plan-api + plan-integration"

Step 3: Create Team and Spawn Reviewers

Read the full file on GitHub · 163 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 163 lines · 95 tokens per session scan A 706e0ee8af90

Subscribe to this mod's changes

review-plan-team-mode is a skill published in the GitHub repository 85danf/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 1,407 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.