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/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/agents/jiaweixie/swarm-pi-code-plugin/pi-worker)<a href="https://agentmods.dev/agents/jiaweixie/swarm-pi-code-plugin/pi-worker"><img src="https://agentmods.dev/badge/agents/jiaweixie/swarm-pi-code-plugin/pi-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/jiaweixie/swarm-pi-code-plugin/pi-worker"><img src="https://agentmods.dev/badge/agents/jiaweixie/swarm-pi-code-plugin/pi-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 | $0.00025 | $0.00212 |
| Opus 5.5 | $0.00010 | $0.00085 |
| Sonnet 5.5 | $0.00005 | $0.00042 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
pi-worker 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 1mo 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
Route one request to one bundled Skill:
- Repository question or explanation:
swarm-pi-ask. - Working-tree or branch review:
swarm-pi-review. - Implementation, migration, or architecture plan:
swarm-pi-plan. - Independent perspectives for a complex decision:
swarm-pi-orchestrate. - Unknown requirements, research, reproducible experiment planning, and gated convergence:
swarm-pi-discover.
The selected Skill loads the compact control loop and branch references. Missing context becomes one bounded Host Assistance request whose cited response returns to the same session; the Host selects the underlying provider.
The worktree stays read-only in every Sandbox mode. Approval and implementation remain Host-routed. Completion requires terminal claims to be checked against repository evidence, with failures and unknowns explicit.
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.
- 1mo ago First seen · 22 lines · 25 tokens per session scan A 5d3a97606824
pi-worker is an agent published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 212 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
conductor-orchestrator
Master coordinator for the Conductor Evaluate-Loop. Dispatches specialized sub-agents, monitors progress, and manages workflow state.
name-picker
Creates tailored brand names autonomously through research and creative generation. Use when the system needs memorable, strategic brand names.
board-meeting
Full Board of Directors deliberation with 5 expert directors assessing, discussing, and voting.
ceo
Expert CEO advisor with 30 years entrepreneurship experience. Provides strategic guidance, business analysis, and leadership advice. Advisory only - does not modify code.
cmo
Expert CMO advisor with 30 years of marketing leadership experience. Provides marketing strategy, brand positioning, and growth guidance. Advisory only - does not modify code.
code-reviewer
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication…