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.
git clone --depth 1 https://github.com/ChrisMckerracher/claude-dream-teamWrote 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/commands/chrismckerracher/claude-dream-team/epic)<a href="https://agentmods.dev/commands/chrismckerracher/claude-dream-team/epic"><img src="https://agentmods.dev/badge/commands/chrismckerracher/claude-dream-team/epic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/chrismckerracher/claude-dream-team/epic"><img src="https://agentmods.dev/badge/commands/chrismckerracher/claude-dream-team/epic.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00842 |
| Opus 5 | $0.00015 | $0.00421 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
epic 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 10d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic Workflow
You are starting an Epic workflow with the Dream Team. Follow these steps precisely.
Step 1: Understand the Request
Read the user's input carefully. If the request is vague, ask clarifying questions using AskUserQuestion before proceeding:
- What is the desired outcome?
- Who is the target user?
- Are there technical constraints?
- Is there UI/UX work involved?
Step 2: Set Up the Team
-
Create a team using TeamCreate:
- Team name:
epic-{short-slug}(derived from the feature name) - Description: Brief description of the epic
- Team name:
-
Create the initial task list using TaskCreate:
- Task 1: "Product brief and feature files" (assign to Product agent)
- Task 2: "Technical design document" (assign to Architect agent)
- Task 3: "Review planning docs" (assign to yourself - Team Lead)
- If UI work involved: Task 4: "Design system scan and design spec" (assign to UI/UX Designer)
Step 3: Planning Phase
-
Determine if Product and Architect can work in parallel:
- Parallel: If the epic is well-defined and both can work independently
- Sequential: If Product needs to define scope before Architect can design
-
Spawn agents using the Task tool:
- Product agent (
dream-team:product): Provide the user's request and ask for product brief + .feature files - Architect agent (
dream-team:architect): Provide the request and ask for technical design doc - Tell both agents to communicate with each other via SendMessage
- Product agent (
-
Wait for both to complete. Review their output together.
-
If you have feedback:
- Send specific notes to the relevant agent via SendMessage
- Wait for revisions
- Repeat until satisfied
-
If UI/UX work is involved:
- Spawn UI/UX Designer agent (
dream-team:ui-ux-designer) - Have them scan the existing codebase for design patterns
- Have them create design specs for the new UI elements
- Spawn UI/UX Designer agent (
Step 4: User Review Gate
Notify the user:
- "The planning phase is complete. Here's a summary of the plan:"
- Present a concise summary of Product brief, Technical design, and Design spec (if applicable)
- Ask the user to review and approve before proceeding
- This is a blocker - do not proceed without user approval
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.
- 10d ago First seen · 99 lines · 30 tokens per session scan A 95af4f0148b2
epic is a command published in the GitHub repository ChrisMckerracher/claude-dream-team (5 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 842 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.