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.
npx skills add budagov-lab/DreamTeam --skill planner-task-decompositiongit clone --depth 1 https://github.com/budagov-lab/DreamTeamWrote 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/skills/budagov-lab/dreamteam/planner-task-decomposition)<a href="https://agentmods.dev/skills/budagov-lab/dreamteam/planner-task-decomposition"><img src="https://agentmods.dev/badge/skills/budagov-lab/dreamteam/planner-task-decomposition.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 | $0.00032 | $0.00429 |
| Opus 5 | $0.00016 | $0.00215 |
| Sonnet 5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
planner-task-decomposition 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 7d 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.
What it actually says
Planner Task Decomposition
CRITICAL: Planner Delegates to Sub-Planner
Planner MUST NOT create task files directly. Planner creates epic outline, then dispatches Sub-Planner via mcp_task for each epic. Sub-Planner creates task files.
Left/Right: When you need planning, call planner (NOT planner-sub). Planner will call planner-sub per epic.
When to Use
- New goal or epic to implement
- User requests task breakdown or planning
- Meta Planner requests task resplitting
Workflow (Planner)
- Read context:
.dreamteam/memory/architecture.md,.dreamteam/memory/summaries.md - Break into epics — 5–50 blocks. Write
.dreamteam/docs/epics/[goal-slug].mdwith epic titles + short descriptions. - For each epic — mcp_task with
subagent_type: planner-sub, prompt:- "Expand epic N: [title + 5–10 line desc]. Create TXXX–TYYY. Dependencies: [Tprev]." (First epic: deps [].)
- After each Sub-Planner — Terminal:
python -m dreamteam sync-tasks - Return when all epics expanded. No task limit — system supports thousands of tasks.
What Sub-Planner Does (planner-sub)
- Reads epic + ID range from Planner prompt
- Creates task files in
.dreamteam/tasks/ - Returns "DONE. Created TXXX–TYYY (N tasks)."
Rules
- No circular dependencies
- Small tasks: 1–3 files per task, ~15–30 min each, single deliverable
- Dependencies must reference existing task IDs
- Planner never creates task_XXX.md — only Sub-Planner does
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.
- 7d ago First seen · 41 lines · 32 tokens per session scan A 14d64bf784f0
planner-task-decomposition is a skill published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 429 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 2026-08-31.
Other skills, from other repositories
migrate-spec
Detect GSD, spec-kit, or BMAD spec artifacts and transform them into bigpowers YAML layout (state.yaml, release-plan.yaml, epics/, requirements/, plans/, ADRs). Use when migrating foreign spec docs.
extract-design
Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose. Use when the user has an HTML prototype and wants a DESIGN.md to anchor their project's visual identity, or when seed-conventions has just scaffolded a…
request-review
Dispatch a fresh reviewer agent with a clean context to critique the code after audit-code passes. The reviewer has no shared state with the coding agent and gives a genuine second opinion. Use after audit-code passes, before committing, or when user wants an independent code review.
run-benchmark
Run skill quality benchmarks from specs/benchmarks/ definitions — N-run with/without-skill delta grading, train/validation split, pass@k + benchmark.json reports. Use before and after evolve-skill to prove quality changes are improvements, not regressions.
wire-observability
Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development.
enforce-first
Apply the F.I.R.S.T test quality rubric (per CONVENTIONS.md §Tests) to a test suite or individual tests. Use when develop-tdd is writing tests, when test quality needs to be checked, or when user mentions F.I.R.S.T or "test quality".