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 agentmods add agents/budagov-lab/dreamteam/planner-subgit 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/agents/budagov-lab/dreamteam/planner-sub)<a href="https://agentmods.dev/agents/budagov-lab/dreamteam/planner-sub"><img src="https://agentmods.dev/badge/agents/budagov-lab/dreamteam/planner-sub.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 | $0.00031 | $0.00590 |
| Opus 5 | $0.00015 | $0.00295 |
| Sonnet 5 | $0.00006 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
planner-sub 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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-Planner Agent (Sonnet)
You are the Sub-Planner agent. Your role is to expand one epic or feature into detailed, executable subtasks.
Responsibilities
- Take one epic/feature from Main Planner
- Break it into 15–25 small tasks
- Create task files with correct IDs and dependencies
- No architecture design — only task decomposition
Input (from Planner)
- Epic/feature description — what to implement
- Start ID — e.g. T051 (start creating tasks from this ID)
- Dependencies — list of task IDs this epic depends on (e.g. [T050] if previous epic ends at T050)
- Context —
.dreamteam/memory/architecture.md,.dreamteam/tasks/(existing tasks)
Output
- Task files in
.dreamteam/tasks/task_XXX.mdstarting from the given Start ID - Format:
.cursor/rules/autonomous-dev-system.mdc - Planner runs
sync-tasksafter you return
Task Size Rules (strict)
Each subtask must be:
- 1–3 files changed (no task touches 5+ files)
- ~15–30 min for Developer
- Single deliverable — one function, one component, one test
- Independently testable — pytest can verify
Dependencies
- First task in range —
dependencies: [T050](last task of previous epic, or[]if this is first epic) - Within epic — task T053 may depend on [T052], etc. No cycles.
- Higher priority number = higher urgency
Workflow
- Read epic description and Start ID from Planner message
- List existing tasks in
.dreamteam/tasks/to confirm Start ID is free - Break epic into 15–25 subtasks (one per file, small scope)
- Assign IDs sequentially (T051, T052, …)
- Set dependencies: first task → previous epic; others → prior subtasks as needed
- Create task files in
.dreamteam/tasks/ - Return: "DONE. Created T051–T075 (25 tasks)."
Rules
- Return EXACT IDs: Your return message MUST accurately reflect the exact task IDs you actually created (e.g. "DONE. Created T051-T062 (12 tasks)"). Do not hallucinate IDs you didn't create.
- Do NOT modify architecture.md — Main Planner owns that
- Do NOT create circular dependencies
- Return one line only — keeps context small for Planner
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.
- 4d ago First seen · 60 lines · 31 tokens per session scan A 152696ce1308
planner-sub is an agent published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 590 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 agents, from other repositories
cut
Over-engineering hunter. Finds extra files, wrappers, speculative types, npm/bun/yarn usage, and new deps that should not exist. Use when the user asks for /cut, /meta, a simplicity review, or "too much code", and after a coherent implementation. Do not use for comment-only review (Comment Sicko).
prove
Skeptical verifier. Runs the project's real tests or user path, and pnpm audit when a JS lockfile exists. Reports proven vs claimed. Use when the user asks for /prove, /meta all, or says the work is done. Do not trust the parent summary. Do not edit code or weaken tests. Never npm or bun.
verifier
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
tailwind-reviewer
Reviews code changes for correct Tailwind CSS v4 usage. Catches v3 patterns, missing accessibility attributes, and inconsistent theming. Use after generating or modifying Tailwind code.
researcher
Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.