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 tmargolis/career-navigator --skill setup-transcribegit clone --depth 1 https://github.com/tmargolis/career-navigatorWrote 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/tmargolis/career-navigator/setup-transcribe)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/setup-transcribe"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/setup-transcribe/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/tmargolis/career-navigator/setup-transcribe"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/setup-transcribe.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 | $0.00071 | $0.01108 |
| Opus 5.5 | $0.00028 | $0.00443 |
| Sonnet 5.5 | $0.00014 | $0.00222 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
setup-transcribe 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 27d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install the local mcp-transcribe MCP server so /career-navigator:interview-capture can transcribe recorded interview audio files. This walks a non-technical user through the same steps mcp-transcribe/README.md documents for the command line — but Claude runs them, with confirmation before anything is installed or changed.
This is optional. Skip it entirely if the user doesn't plan to use interview-capture.
1. Check whether it's already installed
Check whether a tool named backend_info (from mcp-transcribe) is already available in this session. If it is, call it, report the active backend, and stop — nothing to install.
If not, continue.
2. Locate the plugin directory
Resolve the absolute path to this plugin's mcp-transcribe/ directory (the same repo skills/setup-transcribe/SKILL.md lives in). If it can't be found (e.g. the plugin was installed as a zip without this optional directory), tell the user:
Interview transcription setup isn't available from this install — it needs the
mcp-transcribe/folder from the Career Navigator GitHub repo. Clone or download the repo from https://github.com/tmargolis/career-navigator and re-run this from inside it.
Then stop.
3. Check prerequisites
Run via Bash (read-only checks, no confirmation needed):
command -v uv; command -v ffmpeg; command -v brew
Report which are present. Two cases:
Homebrew missing (uv and/or ffmpeg also missing): This flow only automates the Homebrew path (macOS/Linuxbrew). Tell the user to install uv and ffmpeg themselves (point to https://docs.astral.sh/uv/getting-started/installation/ and https://ffmpeg.org/download.html), then re-run this skill. Stop.
Homebrew present, uv and/or ffmpeg missing: Tell the user exactly what will run and why, then ask for explicit confirmation before running it:
This needs
uvandffmpeginstalled via Homebrew. I'll run:brew install uv ffmpeg. OK to proceed?
Only after a clear yes, run it via Bash. If it fails, show the error and stop — do not retry silently.
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.
- 27d ago First seen · 101 lines · 71 tokens per session scan A f4a001936621
setup-transcribe is a skill published in the GitHub repository tmargolis/career-navigator (16 stars, last pushed 27d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,108 once invoked, about $0.0003 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 2026-09-27.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…