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 commands/miopea/swarm-legacy/testgit clone --depth 1 https://github.com/miopea/swarm-legacyWrote 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/miopea/swarm-legacy/test)<a href="https://agentmods.dev/commands/miopea/swarm-legacy/test"><img src="https://agentmods.dev/badge/commands/miopea/swarm-legacy/test.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 | $0.00013 | $0.00372 |
| Opus 5 | $0.00006 | $0.00186 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
test 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.
What it actually says
Run the swarm test suite and summarize the results.
Steps
- Run the test runner (adjust timeout as needed):
uv run swarm test --timeout 300
This will:
- Launch a synthetic test project on port 9091
- Monitor worker activity with
[STATE],[TASK],[DRONE],[QUEEN]prefixed console output - Auto-shutdown when all tasks complete (or on timeout)
- Generate a markdown report
-
Watch the console output for progress indicators:
[STATE]— worker state transitions[TASK]— task assignments and board updates[DRONE]— drone decisions (auto-approve, escalate, etc.)[QUEEN]— queen analysis results[HIVE]— hive lifecycle events (complete, workers changed)[ESCALATE]— escalation warnings
-
When the test completes, read the report file path from the output.
-
Read the report and summarize:
- Exit code (0=success, 1=failure, 2=timeout)
- Number of tasks completed vs total
- Key metrics (drone decisions, queen calls, state transitions)
- Any notable observations or failures
- AI analysis highlights (if present in the report)
Options
--port N— use a different port (default: 9091 from config)--timeout N— seconds before auto-shutdown (default: 300)--no-cleanup— keep the test session and temp dir for debugging-c CONFIG— use a specific swarm.yaml
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 · 44 lines · 13 tokens per session scan A a1432453af35
test is a command published in the GitHub repository miopea/swarm-legacy (9 stars, last pushed 5d ago), licensed MIT. It adds 13 tokens to every session and 372 once invoked, about $0.0001 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
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
review
Manage AO code reviews of a worker's PR.
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
inbox
Check and respond to inter-agent messages.
recover-context
Strategically explore the most recent parent session from the session lineage (shown in the first user message) to extract the full context of the last task.
orchestrate
複数Issueを並列オーケストレーション（準備→開発→PR→マージ→UAT→修正ループ→完了）.