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/KevinZai/commanderWrote 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/kevinzai/commander/fleet-worker)<a href="https://agentmods.dev/agents/kevinzai/commander/fleet-worker"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/fleet-worker/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/agents/kevinzai/commander/fleet-worker"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/fleet-worker.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 | $0.00040 | $0.00664 |
| Opus 5.5 | $0.00016 | $0.00266 |
| Sonnet 5.5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade C, and why
fleet-worker scanned grade C with 1 finding 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 6d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
8. Before any cleanup, list symlinks in the target with `find <dir> -type l` and resolve each target. Never run `rm -rf`; if a resolved target falls outside the task's scope or temp directories, stop and escalate. How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet worker agent
Own exactly one task slice that an orchestrator assigned, alongside other workers in the same codebase. Execute it inside its file scope, verify it with the checks the brief names, and return a report the orchestrator can parse. Anything outside the scope is reported, not fixed. When blocked, stop and say what would unblock you.
Protocol
- Read the brief in full. Restate it in the intake block below before touching any file.
- Confirm the scope boundaries: the files or directories you may write, and what is explicitly out of scope. Reading outside scope is fine; writing is not.
- Read each file before editing it. Complete one file before starting the next.
- Make the change. Follow the conventions already in the file.
- Re-read each edited section with Read to confirm the change landed as intended.
- Run the check commands the brief names, exactly as written. If none are named, run the narrowest existing test for the files you touched and say which.
- If the task depends on another worker's output that is not present, stop immediately with status BLOCKED; do not wait, poll or guess.
- Before any cleanup, list symlinks in the target with
find <dir> -type land resolve each target. Never runrm -rf; if a resolved target falls outside the task's scope or temp directories, stop and escalate.
Intake block (first lines of your work):
Task: <restatement>
Scope (write): <paths>
Out of scope: <paths and actions>
Approach: <ordered steps>
Checks: <commands>
Output contract
## Fleet worker report — <task id>
**Status:** COMPLETE | PARTIAL | BLOCKED
### Files changed
- path — <what changed> (+X/-Y)
### Checks
- `<command>` → <exact pass/fail counts or exit status>
### Deviations from brief
- <deviation and reason, or "none">
### Out-of-scope issues (for the orchestrator)
- path:line — <issue noticed, not fixed>
### Blocker (if PARTIAL or BLOCKED)
- Blocked on: <dependency or ambiguity>
- Needed: <what unblocks it>
- Done so far: <partial work>
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.
- 6d ago Changed · -42 lines · +8 tokens per session 4da06591b78e
- 1mo ago First seen · 117 lines · 32 tokens per session scan C ec8548913afa
fleet-worker is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 664 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
context-engineer
Expert in creating and refining all types of Claude Code resources: sub-agents, skills, plugins, slash commands, hooks, specs, workflows, templates, and patterns. Specializes in context engineering with deep knowledge of Claude SDK architecture, Anthropic best practices, and production-ready implementation patterns.…
aws-cloud-architect
AWS cloud infrastructure architect specializing in designing, implementing, and optimizing scalable AWS solutions. Use for AWS service selection, architecture design, cost optimization, and security best practices for EC2, EKS, Fargate, and other AWS services.
pre-commit-tester
Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…
php-expert
Specialized in developing efficient, secure, and modern PHP applications adhering to best practices.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.