team-implement-plan

team-implement-plan is a skill for Claude Code from mhylle/claude-skills-collection. It costs 82 tokens per session (2,577 once invoked), scanned A, original, MIT.

A small review team for carrying out a software implementation plan. One agent writes the code, another checks it critically, and an optional third agent keeps larger plans consistent across phases.

In plain words
What is it for?
Use it for moderate or complex plans where implementation and review should happen together. It can write code, run builds and tests, inspect changes, and request fixes.
Why use it?
It adds a second set of eyes while the work is being done, helping catch quality problems and missed requirements that ordinary automated checks may not find.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; positional $N argument.

Part of the devflow plugin — 38 skills, 13 agents, 5 hooks shipped together

Good fit Use it for moderate or complex plans where implementation and review should happen together. It can write code, run builds and tests, inspect changes, and request fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mhylle/claude-skills-collection/team-implement-plan
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 mhylle/claude-skills-collection --skill team-implement-plan
Clone the repo
git clone --depth 1 https://github.com/mhylle/claude-skills-collection

Made for: Claude Code.

Or install devflow, the plugin that ships this one along with the rest of its 38 skills, 13 agents, 5 hooks.

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 team-implement-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/team-implement-plan/github.svg)](https://agentmods.dev/skills/mhylle/claude-skills-collection/team-implement-plan)
Your own site
<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/team-implement-plan"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/team-implement-plan/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 team-implement-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/team-implement-plan"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/team-implement-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00082 $0.02577
Opus 5 $0.00041 $0.01288
Sonnet 5 $0.00016 $0.00515
Haiku 4.5 $0.00008 $0.00258

Measured 12d ago against content hash afad87dffd5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

team-implement-plan scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

b. Run integration tests (curl endpoints, check UI, verify behavior)
skills/team-implement-plan/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Implement Plan (Small Review Team)

Overview

This skill executes implementation plans using a small team of 2-3 members. Unlike the solo implement-plan which uses an orchestrator/subagent pattern, this skill has teammates that implement code directly and review each other's work adversarially.

Team composition:

  • Implementer: Writes code directly using Write/Edit/Bash. Runs build/lint/test
  • Reviewer: Reviews code changes, checks ADR compliance, runs integration tests. Sends fix requests
  • Integrator (optional, for plans with 4+ phases): Monitors cross-phase consistency, handles plan sync

When to use this vs implement-plan:

  • Use implement-plan for simple plans (1-3 phases, clear requirements, ~30-40K tokens/phase)
  • Use team-implement-plan for quality-sensitive plans where adversarial review matters (~60-80K tokens/phase)
  • Use team-implement-plan-full for large plans with parallel phases (~100-150K tokens/wave)

Reference: See references/team-lifecycle.md for team lifecycle and references/quality-pipeline-distribution.md for pipeline distribution.

Initial Response

When invoked with a plan path:

"I'll set up a small implementation team. An Implementer will write code while a Reviewer independently checks quality. Let me read the plan and set up the team."

Workflow

Phase 1: Plan Reading & Team Setup

Step 1a: Read and validate the plan

Read($0)  # Plan path from argument

Validate the plan has:

  • Implementation phases with objectives
  • Tasks per phase
  • Exit conditions per phase
  • Dependencies between phases

If the plan is missing required sections, inform the user and stop.

Step 1b: Check existing progress

TaskList  # Check for existing tasks from this plan

If tasks exist with some completed, resume from the first incomplete phase. If no tasks exist, the plan was created without task bootstrapping — create tasks now.

Step 1c: Determine team size

Plan Size Team
1-3 phases Implementer + Reviewer (2 members)
4+ phases Implementer + Reviewer + Integrator (3 members)

Read the full file on GitHub · 322 lines

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. 12d ago First seen · 322 lines · 82 tokens per session scan A afad87dffd5f

Subscribe to this mod's changes

team-implement-plan is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 9d ago), licensed MIT. It adds 82 tokens to every session and 2,577 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.