team-feature

A command for splitting one software feature into separate work streams for multiple coding agents. Each agent is assigned different files and dependencies are tracked.

In plain words
What is it for?
Use it to plan and implement features in parallel, assign file ownership, define connections between work streams, and check the combined result.
Why use it?
It reduces conflicts when several agents edit the same project at once. It also helps coordinate work that must happen in a particular order.

Command

Part of the agent-teams plugin — 6 skills, 7 commands, 4 agents 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 commands/wshobson/agents/team-feature
Clone the repo
git clone --depth 1 https://github.com/wshobson/agents

Or install agent-teams, the plugin that ships this one along with the rest of its 6 skills, 7 commands, 4 agents.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 873 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 $0.00014 $0.00873
Opus 5 $0.00007 $0.00436
Sonnet 5 $0.00003 $0.00175
Haiku 4.5 $0.00001 $0.00087

Measured 3d ago against content hash be9dd1328f6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-feature 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 3d 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.

plugins/agent-teams/commands/team-feature.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Feature

Orchestrate parallel feature development with multiple implementer agents. Decomposes features into work streams with strict file ownership, manages dependencies, and verifies integration.

Pre-flight Checks

  1. Verify CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set
  2. Parse $ARGUMENTS:
    • <feature-description>: description of the feature to build
    • --team-size N: number of implementers (default: 2)
    • --branch: git branch name (default: auto-generated from feature description)
    • --plan-first: decompose and get user approval before spawning

Phase 1: Analysis

  1. Analyze the feature description to understand scope
  2. Explore the codebase to identify:
    • Files that will need modification
    • Existing patterns and conventions to follow
    • Integration points with existing code
    • Test files that need updates

Phase 2: Decomposition

  1. Decompose the feature into work streams:

    • Each stream gets exclusive file ownership (no overlapping files)
    • Define interface contracts between streams
    • Identify dependencies between streams (blockedBy/blocks)
    • Balance workload across streams
  2. If --plan-first is set:

    • Present the decomposition to the user:

      ## Feature Decomposition: {feature}
      
      ### Stream 1: {name}
      Owner: implementer-1
      Files: {list}
      Dependencies: none
      
      ### Stream 2: {name}
      Owner: implementer-2
      Files: {list}
      Dependencies: blocked by Stream 1 (needs interface from {file})
      
      ### Integration Contract
      {shared types/interfaces}
      
    • Wait for user approval before proceeding

    • If user requests changes, adjust decomposition

Phase 3: Team Spawn

  1. If --branch specified, use Bash to create and checkout the branch:
    git checkout -b {branch-name}
    
  2. Use TeamCreate tool to create the team with team_name: "feature-{timestamp}" and description
  3. Spawn a team-lead agent to coordinate
  4. For each work stream, use Agent tool to spawn a team-implementer:
    • name: implementer-{n}
    • subagent_type: "agent-teams:team-implementer"
    • prompt: Include owned files, interface contracts, and implementation requirements

Read the full file on GitHub · 115 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. 3d ago First seen · 115 lines · 14 tokens per session scan A be9dd1328f6c

Subscribe to this mod's changes

team-feature is a command published in the GitHub repository wshobson/agents (39,318 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 873 once invoked, about $0.0001 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 2026-08-30.