team-plan

A planning command that breaks a task into separate workstreams and assigns suitable roles to a team of agents.

In plain words
What is it for?
Use it to form a coordinated team plan for a feature, bug fix, refactor, migration, or other software project.
Why use it?
It helps clarify the work, dependencies, choices, and checkpoints before implementation begins.

Command for Claude Code

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/osmantic/ods/team-plan
Clone the repo
git clone --depth 1 https://github.com/Osmantic/ODS

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,084 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 $0.00012 $0.07084
Opus 5 $0.00006 $0.03542
Sonnet 5 $0.00002 $0.01417
Haiku 4.5 $0.00001 $0.00708

Measured 3d ago against content hash 8e558079c0f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-plan 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.

.claude/commands/team-plan.md · 798 lines

How it starts

The opening of the file, as written. The whole thing — 798 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Team Planner

Analyze a user prompt, decompose it into workstreams, and interactively assign agent roles to form a coordinated team plan.

Arguments

  • $ARGUMENTS - A description of the task, feature, or project to plan for.

Philosophy: Ask Early, Ask Often

This skill should liberally use AskUserQuestion at every decision point. Do NOT assume user intent — validate it. The cost of asking is low; the cost of building the wrong plan is high. When in doubt, ask. Specifically:

  • Before narrowing scope — confirm what's in and out
  • Before committing to an approach — present alternatives
  • After discovering something unexpected — share findings and get direction
  • Between phases — checkpoint progress and confirm next steps
  • When models disagree — let the user break the tie
  • When tradeoffs exist — present them explicitly

The user should feel like a co-pilot throughout the entire planning process, not a rubber stamp at the end.

Workflow

Phase 1: Analyze the Prompt

Read and understand $ARGUMENTS. Identify:

  1. Scope - What is being asked? (feature, refactor, bug fix, migration, research, etc.)
  2. Domains touched - Which parts of the codebase are involved? (installer libs, installer phases, scripts, CLI, dashboard-api, dashboard UI, extensions, Docker config, tests, docs)
  3. Complexity signals - Multi-file? Cross-cutting concerns? External dependencies? Breaking changes?
  4. Risks - What could go wrong? What needs careful attention?

Before proceeding, explore the relevant codebase areas to ground your analysis in reality:

# Identify relevant files
Glob for patterns matching the task domains
Grep for key symbols, functions, or patterns mentioned in the prompt
Read critical files to understand current state
1a. Validate Understanding with User

After initial analysis, always confirm your understanding before proceeding. Do NOT silently assume scope:

AskUserQuestion:
  question: "Here's my understanding of the task. Is this correct, or should I adjust scope?"
  header: "Scope"
  multiSelect: false
  options:
    - label: "Looks correct"
      description: "<1-2 sentence summary of your understanding of scope and domains>"
    - label: "Broader scope"
      description: "I want this to also cover <adjacent areas you identified but weren't sure about>"
    - label: "Narrower scope"
      description: "Focus only on the core ask — skip <peripheral concerns you identified>"

Read the full file on GitHub · 798 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 · 798 lines · 12 tokens per session scan A 8e558079c0f1

Subscribe to this mod's changes

team-plan is a command published in the GitHub repository Osmantic/ODS (5,819 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 7,084 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.