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-audio-briefgit 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-audio-brief)<a href="https://agentmods.dev/skills/lunchpaillola/pipa-skills/pipa-audio-brief"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-audio-brief/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-audio-brief"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-audio-brief.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 | $0.00111 | $0.03599 |
| Opus 5 | $0.00056 | $0.01800 |
| Sonnet 5 | $0.00022 | $0.00720 |
| Haiku 4.5 | $0.00011 | $0.00360 |
Grade C, and why
pipa-audio-brief scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://here.now/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://here.now/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Artifact Audio Brief
Create a listenable brief for work produced by AI agents, coding tools, or document workflows.
Use this when the user wants to understand what an agent did, what a document says, what changed in a PR, what matters in a research report, or where to focus their review without reading everything line by line.
The brief should answer the casual request: "Give me the brief."
Primary goal: fast orientation, useful judgment, and an immersive listen-first review experience. Turn a source artifact into an intelligent spoken orientation: the story of the artifact, what matters, what needs attention, and what the listener should do next.
Output goal: create a deterministic single-page listening experience with browser speech by default, publish it with here.now, and return the here.now URL. Piper and Kokoro are optional generated-audio presets when the user explicitly asks for local generated audio and accepts the setup, time, and memory requirements.
Communication style contract: apply ~/.pipa/communication-style.md when present; otherwise apply skills/pipa/references/communication-style.md. Presentation preferences never override this skill's workflow, output contract, safety rules, or publishing gates.
Workflow
Before executing, copy this checklist and keep it updated in your working notes:
Audio Brief Progress
- [ ] Step 1 complete: source and listening goal confirmed
- [ ] Step 2 complete: source extracted with safety and provenance recorded
- [ ] Step 3 complete: 300-350 word spoken brief script created
- [ ] Step 4 complete: browser speech mode selected by default, or optional Piper/Kokoro audio generated and duration-checked
- [ ] Step 5 complete: deterministic single-page listening UI generated from template
- [ ] Step 6 complete: here.now installed/available and page published
- [ ] Step 7 complete: local artifacts cleaned after successful publish, or debug artifacts preserved intentionally
- [ ] Step 8 complete: here.now URL returned with status and blockers
What ships with it
19 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.
- evals/evals.json 7.9 KB
- evals/trigger-eval-set.json 1.2 KB
- PRODUCT.md 2.1 KB
- references/audio-brief-script.md 6.1 KB
- references/audio-generation-and-fallbacks.md 12 KB
- references/dogfood-implementation-playbook.md 5.2 KB
- references/here-now-publishing.md 2.2 KB
- references/listening-page-template.md 25 KB
- references/local-review-bundle.md 4.3 KB
- references/single-page-ui-contract.md 4.9 KB
- references/source-extraction.md 3.9 KB
- scripts/generate-audio-job.sh 18 KB runs code
- scripts/kokoro_onnx_generate.py 3.5 KB runs code
- scripts/publish.py 9.2 KB runs code
- scripts/publish.sh 435 B runs code
- scripts/render-listening-page.py 17 KB runs code
- scripts/setup-kokoro.sh 4.4 KB runs code
- scripts/setup-piper.sh 3.9 KB runs code
- scripts/test-generate-audio-job.sh 4.7 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.
- 12d ago First seen · 233 lines · 111 tokens per session scan C 23a17b24b183
pipa-audio-brief is a skill published in the GitHub repository lunchpaillola/pipa-skills (3 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 3,599 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoresearch
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill…
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.
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
compound
Capture and compound learnings from conversations into reusable commands and skills through interactive dialogue.
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…