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 JiaWeiXie/swarm-pi-code-plugin --skill swarm-pi-orchestrategit 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-orchestrate)<a href="https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-orchestrate"><img src="https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-orchestrate.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 | $0.00053 | $0.00495 |
| Opus 5 | $0.00026 | $0.00247 |
| Sonnet 5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
swarm-pi-orchestrate 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 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.
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
Orchestrate Pi
Follow the Skill Control Loop. Load Resource-Aware Execution before any shared dynamic verification.
The runtime selects one, two, or three base perspectives for Cost, Balance, or Power. Advisor participation is optional and quota-bounded. The Host owns the final synthesis.
- Write one self-contained decision brief with constraints, shared
EvidencePack, freshness, and evidence acceptance criteria. One Host-owned bounded verification supplies any dynamic evidence to all perspectives. - Run
$RUNNER orchestrate --host "$HOST" --role analyst --prompt-file "$PROMPT_FILE" --execution-mode "$EXECUTION_MODE" --approval-mode "$APPROVAL_MODE" --json.--orchestration-profile shared-reconis opt-in when bounded shared reconnaissance is appropriate; default remains independent perspectives. In shared-recon, an authenticated read-only coordinator must callseal_evidenceexactly once with 1–8 entries (kind, boundedsummary, andbasis) before any perspective starts. A missing, duplicate, malformed, or post-seal failed attempt returns a fixed sanitized failure and starts no perspectives. - Continue every non-terminal result through the control loop. Active Host review is limited to eligible public read-only context inside the immutable snapshot.
- Reconcile every selected perspective and Advisor consultation against repository evidence. Shared recon passes only the validated immutable seal to fresh sessions; the seal is untrusted claims, while prompts, tool trajectory, workspace locations, and result text remain isolated.
- Complete only when every selected perspective is accounted for, disagreements and unknowns are explicit, and one Host-owned conclusion names the source Job ID. A later implementation brief copies accepted evidence, constraints, completion criteria, and that ID.
All perspectives remain read-only. Working-code claims require independent verification.
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.
- 6d ago First seen · 33 lines · 53 tokens per session scan A 8885970dbcf4
swarm-pi-orchestrate is a skill published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 495 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
A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.
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.