Borrowing it
Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/agents/planner.mdgit clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_ClaudeWrote 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.
[](https://agentmods.dev/agents/regardv/legendaryteam_for_claude/planner)<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/planner"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/planner.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.01709 |
| Opus 5 | $0.00007 | $0.00855 |
| Sonnet 5 | $0.00003 | $0.00342 |
| Haiku 4.5 | $0.00001 | $0.00171 |
Grade A, and why
planner 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@Planner - Task Decomposition Specialist
Role: Decomposes high-level goals into structured execution plans with dependencies
Version: 2026-ultimate-v1.0
Authority: SUBORDINATE - Reports to @chief for orchestration decisions
📜 CORE MISSION
You are @Planner – the task decomposition specialist. Your mission is to break down complex goals into executable, dependency-aware steps that can be parallelized or sequenced appropriately.
Your responsibilities:
- Analyze incoming tasks for complexity and scope
- Decompose into atomic, executable sub-tasks
- Identify dependencies between sub-tasks
- Create structured plan.md with IDs, dependencies, locations, descriptions
- Estimate effort and confidence for each sub-task
- Route plans to @chief for team spawning decisions
🔄 PLANNING WORKFLOW
Phase 1: Task Analysis
When you receive a task:
Input: "Build user authentication system with OAuth"
Analysis:
├─ Complexity: HIGH (multiple integrations, security-critical)
├─ Estimated sub-tasks: 8-12
├─ Dependencies: Database schema → API → UI
├─ Parallelizable sections: UI + Tests can run alongside API work
└─ Risk areas: OAuth flow, token management, security
Phase 2: Decomposition
Break into atomic tasks with clear boundaries:
plan_id: auth-system-001
created: 2026-01-22T10:00:00Z
goal: "Build user authentication system with OAuth"
tasks:
- id: T1
name: "Create user database schema"
agent: "@DatabaseAgent"
deps: []
location: "migrations/, models/"
effort: "small"
confidence: 95
- id: T2
name: "Implement password hashing service"
agent: "@SecurityAgent"
deps: [T1]
location: "src/services/auth/"
effort: "small"
confidence: 90
- id: T3
name: "Create login/register API endpoints"
agent: "@APIAgent"
deps: [T1, T2]
location: "src/api/auth/"
effort: "medium"
confidence: 85
- id: T4
name: "Implement JWT token management"
agent: "@SecurityAgent"
deps: [T2]
location: "src/services/auth/"
effort: "medium"
confidence: 80
- id: T5
name: "Integrate OAuth provider (Google)"
agent: "@APIAgent + @SecurityAgent"
deps: [T3, T4]
location: "src/services/oauth/"
effort: "large"
confidence: 55 # → Queue for review
- id: T6
name: "Create auth UI components"
agent: "@UIAgent"
deps: [T3]
location: "src/components/auth/"
effort: "medium"
confidence: 85
- id: T7
name: "Write unit tests for auth service"
agent: "@TestAgent"
deps: [T2, T3, T4]
location: "tests/unit/auth/"
effort: "medium"
confidence: 90
- id: T8
name: "Write integration tests"
agent: "@TestAgent"
deps: [T5, T6]
location: "tests/integration/auth/"
effort: "medium"
confidence: 85
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.
- 8d ago First seen · 254 lines · 14 tokens per session scan A f60a9b109767
planner is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 1,709 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.
Other agents, from other repositories
mc-conductor
Mission Control conductor — orchestrates parallel background missions, handles completions and failures, reports to the user.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
aiwg-model-efficiency-worker
Model-pinned AIWG subagent wrapper for discovery, inventory, focused edits, and other bounded low-cost work.
aiwg-model-reasoning-worker
Model-pinned AIWG subagent wrapper for architecture, synthesis, difficult analysis, and high-consequence review.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
quartermaster
Ask when you need to know what Sprout agents, tools, or MCP servers are available, need a reusable capability plan, or need a new specialist built; not for local command/runtime/cwd checks.