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 nweii/agent-stuff --skill audit-transcriptiongit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/audit-transcription)<a href="https://agentmods.dev/skills/nweii/agent-stuff/audit-transcription"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/audit-transcription/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/nweii/agent-stuff/audit-transcription"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/audit-transcription.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 | $0.00059 | $0.01013 |
| Opus 5 | $0.00030 | $0.00507 |
| Sonnet 5 | $0.00012 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
audit-transcription 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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit transcription
Posture
Auto-transcribed text is noisy in domain-specific ways. The user almost always knows what they actually said; you don't. Your job is to flag, not to correct. Every interpretation is a hypothesis until the user confirms it.
You will be wrong about some flags even when you're well-grounded in context. That's fine — it's expected. What's not fine is silently applying corrections the user hasn't seen.
Workflow
1. Read the whole transcript before flagging anything
You can't tell what's mangled until you know the topic and shape. Skim end-to-end first.
2. Pull in domain context the user has documented
Before guessing at vocabulary, check what's actually in the user's world:
- Project notes, AGENTS.md / CLAUDE.md, glossaries
- Related notes the transcript references
- Recent commits, working logs, specs
If a transcribed proper noun doesn't match anything in their documented vocabulary, don't substitute a similar-sounding name from your own knowledge — flag it and ask.
3. Triage into three confidence tiers
| Tier | Example | What to do |
|---|---|---|
| High — recurring vocabulary | A phonetic mishearing of a domain term that appears throughout the transcript (e.g. a tool, product, or library name consistently rendered as a similar-sounding non-word) | Propose find/replace |
| Medium — sentence-level gist | A garbled clause whose meaning is recoverable from context | Propose your interpretation as a question: "I think you were saying X here — does that match?" |
| Low — unrecoverable | A sentence where multiple consecutive words are nonsense and the surrounding context doesn't pin down what was being said | Flag as garbled. Do not reconstruct. |
4. Surface flags as a list, not as edits
Show the user the triage grouped by tier. Wait for their pass:
- They will confirm some, correct others, and reject a few entirely.
- Treat each correction as a context update — apply it across the rest of the transcript before continuing.
- Don't argue. If the user says "that's not a word we use" about one of your guesses, drop it and don't relitigate.
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.
- 8d ago First seen · 85 lines · 59 tokens per session scan A 3286f7f8f771
audit-transcription is a skill published in the GitHub repository nweii/agent-stuff (9 stars, last pushed 20d ago), licensed MIT. It adds 59 tokens to every session and 1,013 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.