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 richawo/yaps-codex-plugin --skill yaps-dictationgit clone --depth 1 https://github.com/richawo/yaps-codex-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/richawo/yaps-codex-plugin/yaps-dictation)<a href="https://agentmods.dev/skills/richawo/yaps-codex-plugin/yaps-dictation"><img src="https://agentmods.dev/badge/skills/richawo/yaps-codex-plugin/yaps-dictation/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/richawo/yaps-codex-plugin/yaps-dictation"><img src="https://agentmods.dev/badge/skills/richawo/yaps-codex-plugin/yaps-dictation.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 | $0.00103 | $0.02493 |
| Opus 5.5 | $0.00041 | $0.00997 |
| Sonnet 5.5 | $0.00021 | $0.00499 |
| Haiku 4.5 | $0.00010 | $0.00249 |
Grade A, and why
yaps-dictation 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yaps Dictation
Use the Yaps desktop app for live microphone capture, transcription, cleanup, context-aware vocabulary, and insertion into the focused desktop field.
Runtime compatibility
Do not try to guess the host or its locality from a user-agent, product name,
or another host signal (for example ChatGPT web versus ChatGPT desktop). Test
the capability this workflow actually needs: before account, model, dependency,
or permission checks, resolve the local Yaps CLI through the plugin runner. The
runner validates it with a bounded, read-only status command. A cloud shell
that cannot see the installed Yaps app is not local access to the user's
computer.
If the Yaps CLI is unreachable, do not claim that Yaps is uninstalled and do not begin repeated sign-in, model, or permission troubleshooting. Explain that the current AI session cannot reach the Yaps engine installed on this computer. Direct the user to a local-capable session on the computer where Yaps is installed: in Claude, that is Claude Code or the Claude desktop app; from ChatGPT web or a cloud session, download or open ChatGPT desktop and retry in a local-capable Work or Codex session. They can also access this feature directly in the Yaps application. If they are already in a local-capable desktop session, offer Download or update Yaps, ask them to open it, and retry. Stop until local reachability is restored; only then follow the availability and setup steps below.
Private operational diagnostics
Run every local Yaps CLI command and every bundled workflow script through the
plugin's scripts/yaps-plugin-runner.mjs. The runner resolves the installed
Yaps CLI when the command begins with yaps, preserves the command's normal
output and exit status, and leaves a small local diagnostic breadcrumb for the
Yaps desktop app:
node <plugin-root>/scripts/yaps-plugin-runner.mjs --action auth.status --stage authentication -- yaps auth status --pretty
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.
- 1mo ago First seen · 163 lines · 103 tokens per session scan A 526030449013
yaps-dictation is a skill published in the GitHub repository richawo/yaps-codex-plugin (2 stars, last pushed 6d ago), licensed MIT. It adds 103 tokens to every session and 2,493 once invoked, about $0.0004 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 skills, from other repositories
note-taker
Capture decisions and facts as durable notes; use when the user makes a decision worth remembering.
reflect
Use Recall Reflect to review AI coding workflow history as a conversation-first timeline and discuss observed patterns before changing behavior. Trigger when the user asks to reflect on a project, review AI coding workflow, inspect workflow friction, discuss repeated corrections, review handoffs, or explore possible…
notion
Read, create, and update Notion pages and databases via the Notion REST API.
sitrep
Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.
any-mcp
Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.
context-minimization
Use when a task runs long and the context window is filling -- large files are being read whole, command output is flooding the transcript, or responses are getting verbose and slow.