team-implement

team-implement is a skill for Claude Code, Codex from bostonaholic/team. It costs 39 tokens per session (432 once invoked), scanned A, original, MIT.

An implementation workflow that writes failing acceptance tests, carries out planned code changes in slices, and runs several independent code reviews.

In plain words
What is it for?
It helps execute an approved plan, write tests first, implement vertical slices, and review the completed changes before delivery.
Why use it?
It catches missing behavior before implementation and checks the result through repeated review gates. The workflow also keeps each change tied to its planned verification.

Skill for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also agents/openai.yaml present. Also seen: names the AskUserQuestion tool.

Part of the team plugin — 88 skills, 13 agents, 2 hooks shipped together

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.

agentmods
npx agentmods add skills/bostonaholic/team/team-implement
Any agent
npx skills add bostonaholic/team --skill team-implement
Clone the repo
git clone --depth 1 https://github.com/bostonaholic/team

Made for: Claude Code, Codex.

Or install team, the plugin that ships this one along with the rest of its 88 skills, 13 agents, 2 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

README.md
[![agentmods](https://agentmods.dev/badge/skills/bostonaholic/team/team-implement.svg)](https://agentmods.dev/skills/bostonaholic/team/team-implement)
Your own site
<a href="https://agentmods.dev/skills/bostonaholic/team/team-implement"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/team-implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00432
Opus 5 $0.00019 $0.00216
Sonnet 5 $0.00008 $0.00086
Haiku 4.5 $0.00004 $0.00043

Measured yesterday against content hash 266693582ad4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

team-implement 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 yesterday.

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.

skills/team-implement/SKILL.md · 41 lines

What it actually says

Team Implement — Execute the Plan

Run the IMPLEMENT phase. Three internal sub-steps:

  1. Test-firsttest-architect writes failing acceptance tests
  2. Slice executionimplementer executes vertical slices with per-slice commits
  3. Code review — 5 parallel reviewers + aggregate hard-gate retry loop

Core contracts

  • Require 7-structure.md, 8-plan.md, and a non-default-branch worktree. Use AskUserQuestion only for missing standalone setup.
  • If 4-repos.md exists, multi-repo work requires worktrees; refuse in-place execution.
  • Seed TodoWrite with Review round 1.
  • Retry as Review round <n+1> (<b> Blocking, <m> Major open).
  • Call the Skill tool with review-severity-tiers before aggregate decisions.
  • Persist ### Cross-model disposition to cross-model-notes.md only when it does not begin Not run:.
  • Full pipeline: do not end the turn; call the Skill tool with team-pr in the same turn.
  • Standalone: after success, suggest /team-pr.

Procedure references

Read each reference completely when reaching that stage. Follow them in order; later stages depend on state and gates established earlier.

  1. Input
  2. Worktree Check
  3. Execution
  4. Quality Loop
  5. Standalone Mode Tradeoffs

Applied principles

Load and apply: principle-progress-tracking.

Files

What ships with it

6 files 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. yesterday Changed · -207 lines · -66 tokens per session 266693582ad4
  2. 2d ago First seen · 248 lines · 105 tokens per session scan A a4a3e4223eb8

Subscribe to this mod's changes

team-implement is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 432 once invoked, about $0.0002 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 2026-09-03.