Borrowing it
Nothing to install: this file belongs to edwinweber/dbt_duckdb_demo_public. 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/edwinweber/dbt_duckdb_demo_public/main/.claude/commands/team.mdgit clone --depth 1 https://github.com/edwinweber/dbt_duckdb_demo_publicWrote 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/edwinweber/dbt_duckdb_demo_public/team)<a href="https://agentmods.dev/commands/edwinweber/dbt_duckdb_demo_public/team"><img src="https://agentmods.dev/badge/commands/edwinweber/dbt_duckdb_demo_public/team/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/edwinweber/dbt_duckdb_demo_public/team"><img src="https://agentmods.dev/badge/commands/edwinweber/dbt_duckdb_demo_public/team.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 | $0.00000 | $0.00412 |
| Opus 5 | $0.00000 | $0.00206 |
| Sonnet 5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
team 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.
What it actually says
Analyse the following task, identify ALL agents from the project team in .claude/agents/ whose expertise is relevant, spawn them, and synthesise their outputs into a single cohesive answer for the user.
Agent roles
investigator— diagnose broken or unexpected behaviour; read-only, evidence-basedarchitect— design decisions, trade-offs, hard-to-reverse choicesengineer— implementation: Python, dbt, Dagster, dlt, DuckDB schema, testswriter— documentation, blog posts, explanations
How to decide which agents to invoke
Invoke every agent whose lens adds something the others would miss. A task rarely needs only one.
| Task type | Agents |
|---|---|
| Pure debug / something is broken | investigator only |
| New feature, no design ambiguity | engineer + writer (if docs needed) |
| New feature with architectural implications | architect → engineer → writer |
| Design question only | architect only |
| Documentation only | writer only |
| Broad question (e.g. "how should we approach X") | architect + engineer (parallel perspectives) |
When in doubt, spawn more rather than fewer — the user asked for the full team.
Execution order
- Parallel: agents with no dependency on each other run simultaneously.
- Sequential:
architectbeforeengineer(design before code);engineerbeforewriter(implementation before docs);investigatorbefore anyone else when the root cause is unknown. - Pass relevant output from earlier agents as context when spawning later ones.
Output
Synthesise all agent responses into one structured answer. Label each section by the agent that produced it so the user knows which lens each part comes from. Do not just concatenate — integrate where the agents agree, and surface disagreements explicitly.
Task
$ARGUMENTS
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 · 38 lines · 0 tokens per session scan A aff20eaea3ea
team is a command published in the GitHub repository edwinweber/dbt_duckdb_demo_public (49 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 412 tokens. 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 commands, from other repositories
migration-status
Parse + summarize the JOBREPORT.md produced by a prior migration run. Surfaces cell pass/fail/fix counts per task, lists the failing cells, and recommends a next-step skill (fixup-cell, resume, or all-clear).
powerbi-adopt
Adopt an existing PBIP project through the governed assess/scaffold path.
seshat-check
Deprecated alias of /seshat-bi:check (kept for one release cycle).
seshat-review
Deprecated alias of /seshat-bi:review (kept for one release cycle).
test
Use skills/data-quality-and-contract-testing/SKILL.md and the relevant references in references/ to define evidence for correctness, freshness, and publish safety.
setup
Install or verify the ADE-Bench harness at /.ade-bench (clones repo, installs CLI, downloads bundled DuckDB databases).