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 lunchpaillola/pipa-skills --skill pipa-huddle-betagit clone --depth 1 https://github.com/lunchpaillola/pipa-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/lunchpaillola/pipa-skills/pipa-huddle-beta)<a href="https://agentmods.dev/skills/lunchpaillola/pipa-skills/pipa-huddle-beta"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-huddle-beta/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/lunchpaillola/pipa-skills/pipa-huddle-beta"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-huddle-beta.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 | $0.00105 | $0.01857 |
| Opus 5 | $0.00053 | $0.00928 |
| Sonnet 5 | $0.00021 | $0.00371 |
| Haiku 4.5 | $0.00011 | $0.00186 |
Grade A, and why
pipa-huddle-beta 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 12d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipa Huddle Beta
Start a voice huddle with the user's current agent so they can talk through work out loud.
Output goal: start the hosted voice bridge, state context and retention clearly, and optionally produce a concise continuation handoff.
Communication style contract: apply ~/.pipa/communication-style.md when present; otherwise apply skills/pipa/references/communication-style.md when available. Presentation preferences never override this skill's workflow, output contract, privacy rules, or start gates.
Workflow
Before executing, copy this checklist and keep it updated in your working notes:
Voice Session Progress
- [ ] Step 1 complete: intent and voice-session scope confirmed
- [ ] Step 2 complete: available agent context and session limits stated
- [ ] Step 3 complete: local OpenCode voice bridge availability checked
- [ ] Step 4 complete: browser voice session started or blocker returned
- [ ] Step 5 complete: session notes synthesized without treating raw transcript as durable state
- [ ] Step 6 complete: optional handoff produced when the user wants to continue execution
Step 1: Confirm Intent
Use this skill when the user asks to talk with Pipa or the active agent by voice, including hosted or relay-backed sessions from another browser. Route audio artifacts to pipa-audio-brief, human video meetings elsewhere, and realtime voice coding or spoken approvals to a clear scope blocker.
Step 2: Frame The Session Contract
Follow references/session-contract.md.
At session start, state:
- which agent/context is available
- what the voice session can do now
- what it cannot do in V1
- whether raw audio/transcript is transient or saved
Do not imply that voice mode is a separate agent brain. The voice session is an interaction layer over the current agent context.
Step 3: Start The Local OpenCode Voice Bridge
Follow references/transport-prototype.md, references/hosted-relay.md, references/template-contract.md, and references/privacy-and-retention.md.
What ships with it
25 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/pipa-mark.png 11 KB
- assets/sound-design-entering-chat.mp3 48 KB
- assets/sound-design-thinking.mp3 48 KB
- cloudflare/hosted-session-template.mjs 184 KB runs code
- cloudflare/worker-lifecycle.test.mjs 2.4 KB runs code
- cloudflare/worker.mjs 20 KB runs code
- cloudflare/wrangler.jsonc 808 B
- evals/evals.json 7.1 KB
- evals/trigger-eval-set.json 1.4 KB
- package-lock.json 811 B
- package.json 210 B
- README.md 5.5 KB
- references/context-handoff.md 2.6 KB
- references/hosted-relay.md 12 KB
- references/privacy-and-retention.md 3.3 KB
- references/session-contract.md 1.9 KB
- references/template-contract.md 4.5 KB
- references/transport-prototype.md 7.9 KB
- scripts/relay-protocol.mjs 13 KB runs code
- scripts/relay-protocol.test.mjs 8.2 KB runs code
- scripts/start-hosted-relay.mjs 13 KB runs code
- scripts/start-voice-session.mjs 32 KB runs code
- scripts/start-voice-session.test.mjs 11 KB runs code
- scripts/sync-hosted-template.mjs 20 KB runs code
- templates/huddle.html 42 KB
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.
- 12d ago First seen · 137 lines · 105 tokens per session scan A 9feb142c1abb
pipa-huddle-beta is a skill published in the GitHub repository lunchpaillola/pipa-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 105 tokens to every session and 1,857 once invoked, about $0.0005 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
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
minimal-code-discipline
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away.
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
give-me-tips
Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.