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/christopherlouet/claude-baseWrote 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/christopherlouet/claude-base/work-team)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/work-team"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-team.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 | $0.00000 | $0.00468 |
| Opus 5 | $0.00000 | $0.00234 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
work-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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WORK-TEAM Agent
Launches a coordinated team of agents (Agent Teams) to parallelize work.
Context
$ARGUMENTS
Goal
Break down a complex task into subtasks and distribute them to specialized agents. Each agent works in parallel on its scope, the lead synthesizes the results.
Workflow
- Check that Agent Teams is enabled (
$CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS= 1) - Analyze the task and choose the appropriate pattern (see below)
- Spawn the agents with clear roles and distinct scopes
- Coordinate via task list, direct messaging, delegate mode if > 3 agents
- Synthesize the results into a consolidated report
- Cleanup: shutdown each agent + resource cleanup
Available patterns
| Keywords | Pattern | Agents |
|---|---|---|
| audit, quality, security | Audit | security-reviewer, perf-analyst, a11y-checker |
| feature, implement | Feature | backend-dev, frontend-dev, test-writer |
| bug, investigate, debug | Debug | 3-5 investigators with different hypotheses |
| review, code review | Review | security-reviewer, perf-reviewer, quality-reviewer |
| Other | Custom | Describe the structure |
Patterns detailed in .claude/skills/agent-teams/patterns.md.
Expected output
- Team: Agents created with roles and scopes
- Consolidated report: Results per agent + synthesis + priorities
- Cleanup: Confirmation of shutdown of all agents
Related agents
| Agent | Usage |
|---|---|
/work:work-explore |
Explore BEFORE launching a team |
/work:work-plan |
Plan BEFORE a Feature pattern |
/qa:qa-audit |
Single-agent alternative to the audit |
IMPORTANT: Always check that Agent Teams is enabled before creating a team.
YOU MUST choose the pattern appropriate to the task.
YOU MUST clean up the team after use (shutdown + cleanup).
NEVER launch more than 5 agents without warning about the token cost.
NEVER have 2 agents work on the same file.
Think hard about the task decomposition before spawning the agents.
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.
- 3d ago First seen · 61 lines · 0 tokens per session scan A dc310c91bc08
work-team is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 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 2026-09-03.
Other commands, from other repositories
release-update
(dev-only) release-update maintainer harness — Claude Code upstream change tracker (release-notes version-delta sweep + docs sync). NOT distributed to user projects.
harness
Manage harness learning subsystem (status/apply/rollback/disable) OR create a harness via natural-language analysis (Context-First Discovery + name derivation + approval gate).
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
context-stats
Display context window usage and token statistics.
migrate
Generate and manage database migrations.
log-decision
Append an architectural decision to the persistent decision log.