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 skills add oaustegard/claude-skills --skill swarming-to-greengit clone --depth 1 https://github.com/oaustegard/claude-skillsWrote 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/skills/oaustegard/claude-skills/swarming-to-green)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/swarming-to-green"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/swarming-to-green/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/skills/oaustegard/claude-skills/swarming-to-green"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/swarming-to-green.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 | $0.00220 | $0.06115 |
| Opus 5.5 | $0.00088 | $0.02446 |
| Sonnet 5.5 | $0.00044 | $0.01223 |
| Haiku 4.5 | $0.00022 | $0.00611 |
Grade A, and why
swarming-to-green 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 2d 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarming to green
A loop that turns a test suite's failures into merged fixes, unattended, for hours:
known.json --cluster by signature--> work items --one headless worker each, own worktree-->
result JSON --serial gate: apply on main, compat check, run smoke + targets + sample,
zero regressions, >=1 target flips--> fast-forward main --> re-check the whole cluster --> repeat
Every mechanism in it fixed a failure that cost hours on 2026-10-12, when Haiku 5.5 workers built hcc (a C compiler in Python) against ~42K tests: 1,051 hub workers, 464 merges, $24.88 of worker spend by 18:30Z. The catalogue of those failures, each with its signal and where it is handled, is references/run-2026-10-12.md.
SK=/mnt/skills/user/swarming-to-green # or <claude-skills clone>/swarming-to-green
SWARM="python3 $SK/scripts/swarm.py" # every command below; --root defaults to the git toplevel
When to use it, and when not
Use it when all hold: a test command can report every test's status as JSON; there are hundreds or more failing tests; a fix can be checked by re-running tests; and the work will run for hours, longer than anyone watches.
| situation | use instead |
|---|---|
| fewer than ten tasks, e.g. setup, a suite builder, a refactor | the Agent tool directly (on 2026-10-12, 3 setup agents were run through claude -p for no gain) |
| a one-off fan-out of independent tasks (judges, extractors, per-file reviews) with no merging | dispatching-subagents |
| which model or effort a worker gets, and how to escalate | agent-routing (this skill's measured answer for test-fix work is in "Which model" below) |
| a fixed multi-step pipeline with no model in the loop | flowing |
| parallel Claude calls from claude.ai chat | orchestrating-chat-agents (orchestrating-agents is its deprecated name) |
| a handful of failing tests | fix them yourself, or one Agent-tool worker per cluster |
| no machine-readable test output yet | write the runner first ("Project setup"), then come back |
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/haiku-cc.toml 5.2 KB
- assets/sibling-brief.md 3.9 KB
- assets/swarm.example.toml 3.5 KB
- assets/worker_prompt.template.md 3.7 KB
- CHANGELOG.md 3.5 KB
- references/config.md 9.0 KB
- references/project-setup.md 5.0 KB
- references/run-2026-10-12.md 14 KB
- references/run-2026-10-13.md 4.8 KB
- references/scaling-out.md 8.3 KB
- scripts/sibling_setup.sh 3.8 KB runs code
- scripts/swarm.py 9.6 KB runs code
- scripts/swarmkit/__init__.py 66 B runs code
- scripts/swarmkit/common.py 9.6 KB runs code
- scripts/swarmkit/compare.py 14 KB runs code
- scripts/swarmkit/config.py 10 KB runs code
- scripts/swarmkit/doctor.py 4.9 KB runs code
- scripts/swarmkit/fake_worker.py 6.0 KB runs code
- scripts/swarmkit/federation.py 19 KB runs code
- scripts/swarmkit/merge.py 34 KB runs code
- scripts/swarmkit/nearness.py 3.9 KB runs code
- scripts/swarmkit/run.py 49 KB runs code
- scripts/swarmkit/selftest.py 28 KB runs code
- scripts/swarmkit/stats.py 6.4 KB runs code
- scripts/swarmkit/testrun.py 9.0 KB runs code
- scripts/swarmkit/worker_result.schema.json 385 B
- scripts/swarmkit/workqueue.py 6.7 KB runs code
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.
- 2d ago First seen · 323 lines · 220 tokens per session scan A f0221a582138
swarming-to-green is a skill published in the GitHub repository oaustegard/claude-skills (153 stars, last pushed yesterday), licensed MIT. It adds 220 tokens to every session and 6,115 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
ephemeral-ci-environment
Get a clean, reproducible ephemeral environment for CI and testing — a fresh root Ubuntu VM with every major toolchain and Docker preinstalled, your GitHub repo auto-cloned in, and the whole thing thrown away after. Per-second billing makes each run cost cents. Use to run tests, reproduce a bug, or validate a build in…
betterthink
Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's instructions file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the…
betterthink
Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's rules file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user…
skill-check
Comprehensive testing and validation of Claude skills. Use this skill whenever the user wants to test, validate, audit, or quality-check a skill — whether they say "test my skill", "check this skill works", "validate my skill", "run skill-check", or anything similar. Also trigger when the user asks things like "does…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.