Borrowing it
Nothing to install: this file belongs to philipyaz/cos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/philipyaz/cos/main/.claude/skills/openwhispr-mcp-setup/SKILL.mdgit clone --depth 1 https://github.com/philipyaz/cosWrote 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/philipyaz/cos/openwhispr-mcp-setup)<a href="https://agentmods.dev/skills/philipyaz/cos/openwhispr-mcp-setup"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/openwhispr-mcp-setup/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/philipyaz/cos/openwhispr-mcp-setup"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/openwhispr-mcp-setup.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 | $0.00214 | $0.04315 |
| Opus 5 | $0.00107 | $0.02158 |
| Sonnet 5 | $0.00043 | $0.00863 |
| Haiku 4.5 | $0.00021 | $0.00432 |
Grade B, and why
openwhispr-mcp-setup scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
grep -q '"openwhispr"' "$REPO_ROOT/.mcp.json" && echo ".mcp.json OK" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "$OPENWHISPR_BRIDGE_URL/mcp" \ How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenWhispr MCP setup (voice-notes add-on — stdio MCP bridge :8002)
Why this exists / architecture
openwhispr is the optional voice add-on. Unlike the core Cos servers (board, calendar,
guard, vault), it has an external-app dependency: it does nothing but expose the
OpenWhispr desktop app's local transcript store, so it only makes
sense on a machine where you actually use OpenWhispr. That's why it lives in its own skill — the
same shape as whatsapp-mcp-setup (which integrates an external app + needs pairing). board /
calendar / guard / vault stay in mcp-bridge-setup; this skill adds the one optional voice
server on top.
It is a single process — mcp/openwhispr-server/server.mjs, a Node stdio MCP server — and
it registers into Cos the same two ways the core servers do:
- Claude Code reaches it over HTTP via a supergateway + launchd BRIDGE on
:8002($OPENWHISPR_BRIDGE_PORT, labelcom.chiefofstaff.mcp-openwhispr, IN.mcp.json). - Claude Cowork Desktop spawns it as a direct stdio
commandentry inclaude_desktop_config.json— identical to how mcp-bridge-setup wires board/calendar/etc.
Claude Code ──HTTP──> localhost:8002/mcp ──supergateway(launchd)──> node openwhispr-server (stdio)
│ reads READ-ONLY (sqlite3 CLI)
└──> ~/Library/Application Support/open-whispr/
transcriptions.db + audio/*.webm
Cowork Desktop ──spawns stdio directly──────────────────────────────────> node openwhispr-server (§4)
The server reads the store read-only (via the sqlite3 CLI; WAL lets it read safely alongside a
running OpenWhispr — though a clean shutdown can transiently remove the -shm file a read-only open
needs, see Gotchas) and owns the watermark (state/watermark.json) that
makes the voice ingest loop idempotent — list_transcripts → route → mark_processed never
re-emits a routed note. The board-side routing is owned by /second-brain-ingest + the voice
recipe; this skill only stands up the plumbing.
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.
- 9d ago First seen · 223 lines · 214 tokens per session scan B 8e88b4931842
openwhispr-mcp-setup is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 214 tokens to every session and 4,315 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 2 findings (reads mcp configuration, 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
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
opencode-plugin-idioms
Event hook payload shapes, session lifecycle timing, toast/TUI-route render boundaries, and child-session tagging conventions for OpenCode server (@opencode-ai/plugin) and TUI (@opencode-ai/plugin/tui) plugins, grounded in the vendored OpenCode source at references/opencode.
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…
self-align
Adversarial self-audit of the Kagan repo through four lenses — code quality & YAGNI, security, spec alignment, docs/AGENTS.md freshness — each finding self-assessed and reported by severity and confidence for the developer to action. Use only when explicitly asked to self-align, audit, or health-check the codebase; it…