Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add karvidsson/agent-ptt/plugin install agent-ptt-voiceWrote 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/karvidsson/agent-ptt/say)<a href="https://agentmods.dev/skills/karvidsson/agent-ptt/say"><img src="https://agentmods.dev/badge/skills/karvidsson/agent-ptt/say.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 | $0.00059 | $0.00290 |
| Opus 5 | $0.00030 | $0.00145 |
| Sonnet 5 | $0.00012 | $0.00058 |
| Haiku 4.5 | $0.00006 | $0.00029 |
Grade A, and why
say scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Speak the message in the Agent PTT voice channel by running:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/say.py" "$ARGUMENTS"
If $ARGUMENTS is empty, compose a one-sentence spoken update yourself from
the current conversation context (what you just did or found), then run the
script with it.
Guidelines for the message:
- Keep it short and speech-friendly — one or two sentences, no markdown, no code, no URLs. It will be synthesized to audio and played on speakers.
- Numbers and identifiers should be listenable ("forty-two tests passed", not "42/42 ✓").
The script joins the channel with this project's own auto-designed voice and
prints 🔊 said: … on success. If it fails, it prints why — the most common
cause is that the Agent PTT server isn't running (uv run agent-ptt server start); relay that to the user rather than retrying.
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 · 27 lines · 59 tokens per session scan A 43ee5311a31c
say is a skill published in the GitHub repository karvidsson/agent-ptt (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 290 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
post-acceptance
This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster", "write promotion content", "create Twitter thread", or mentions post-acceptance conference preparation. Provides comprehensive workflow for presentation, poster, and…
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
remove-ai-marks
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…
cortex-visualize
Launch the interactive Cortex neural-graph visualization (the hypermnesia-mcp-viz MCP). Use when the user says 'show visualization', 'show me the graph', 'visualize memories', 'show memory map', 'open neural graph', 'cortex-visualize', or when a visual overview of the memory system, codebase graph, or session trace…
offline-diagram-triplet
Create editable offline diagrams from an English description or Mermaid source. Use when Codex should emit a triplet: Mermaid source, an editable .excalidraw file for excalidraw.com, and rendered SVG/PNG assets with zero network access.
gemini-audio-tts-music
Generate music (Lyria 3) or synthesize speech (Gemini TTS, single or multi-speaker). Use for soundtracks, voiceovers, demo narration, notification sounds, or audio branding.