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 skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-projectnpx skills add JiaWeiXie/swarm-pi-code-plugin --skill swarm-pi-projectgit clone --depth 1 https://github.com/JiaWeiXie/swarm-pi-code-pluginWrote 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/jiaweixie/swarm-pi-code-plugin/swarm-pi-project)<a href="https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-project"><img src="https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-project.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 | $0.00052 | $0.00399 |
| Opus 5 | $0.00026 | $0.00199 |
| Sonnet 5 | $0.00010 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
swarm-pi-project 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 5d 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
Configure Swarm Pi Project Setup
Follow the Skill Control Loop.
- Run
$RUNNER status --json. Whenworkspace.gitis false, offer onlygit initat the reported root. Approval requires no non-terminal Jobs; the result must be Git-backed, with project files, identity, index, and history unchanged. Migration conflict or block preserves both paths and stops setup. - Start
$RUNNER configure --host "$HOST" --section projectand keep its loopback session active. A save-time storageEPERMtriggers the State storage write boundary: preserve the draft and relaunch with Host approval. - After Save, run
$RUNNER roles list --jsonand$RUNNER status --json. - Complete only when storage directory, model file, state file, migration, routing, and policy are reported. Doctrine is identified as metadata, and Git-init remains a Host decision outside the Web UI.
This repeatable workflow changes only project routing, safety, and profile
settings. New projects default to Adaptive, Host-first, Reversible, and
Discovery gate review; full-access and Autopilot remain opt-in. Existing
Sandbox modes persist, legacy missing Host-first fields remain User-only until
resaved, provider connections stay unchanged, and active Job snapshots remain
immutable.
What ships with it
1 file 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.
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.
- 5d ago First seen · 30 lines · 52 tokens per session scan A fd37f058722b
swarm-pi-project is a skill published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 399 once invoked, about $0.0003 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 skills, from other repositories
review-team
6つの専門レビュアーロールを並列実行し、consensusLevel（複数ロールの合意度）と Tech Lead レポート（top3指摘・blindSpots・consensusSummary）で結果を統合する マルチエージェントレビュー entry skill。 Parallel multi-role review with consensus scoring (consensusLevel) and Tech Lead report. Use when a major release needs exhaustive multi-angle review, or when a single-perspective review…
ultra
Fans the work out as a fleet of parallel Grok and Codex agents billed to their own subscriptions, then synthesizes one result. The peer engine equivalent of ultracode, adding intensity without spending Claude quota on the fleet. Use it for genuinely broad goals, not only explicit asks for intensity.
panel
Convenes a blind Codex and Grok panel on one neutral brief and adjudicates the verdicts.
grok-prompting
Brief writing guidance for composing self contained Grok briefs for coding, review, diagnosis, and second opinion tasks.
grok-result-handling
Internal guidance for presenting Grok companion output back to the user.
smoke
Runs a three probe live smoke wave after a plugin update and reports gate chain health before real work rides it.