scribe

A workflow for turning meeting recordings into trustworthy notes by checking each written claim against the audio. It marks claims as uncertain when the recording or transcript does not support them clearly.

In plain words
What is it for?
Use it to transcribe recordings, identify speakers, preserve important terms, and create notes whose claims can be traced back to the source audio.
Why use it?
It reduces the risk of treating transcription mistakes or invented details as facts in meeting notes.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ooiyeefei/ccc/scribe
Any agent
npx skills add ooiyeefei/ccc --skill scribe
Clone the repo
git clone --depth 1 https://github.com/ooiyeefei/ccc

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 779 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00779
Opus 5 $0.00025 $0.00390
Sonnet 5 $0.00010 $0.00156
Haiku 4.5 $0.00005 $0.00078

Measured 2d ago against content hash 45eab86fa713, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scribe 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 2d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/_thresholds.py, scripts/audit.py, scripts/transcribe.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/scribe/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A summariser cannot hear. Hand it a garbled span and it launders the noise into a clean fact — "some paying customer" becomes "~8,000 users" — and nothing downstream can separate that from a real figure. This skill holds a chain of custody: every claim in the notes traces back to audio the model actually heard well, and a claim whose custody is broken says so.

Scripts are in scripts/. They need a Python with httpx; --provider local also needs faster-whisper.

1. Establish the recording's context

Ask the user, or read it off the surrounding material — the files, the repo, an existing transcript:

  • Language — the ISO code to pin. Left unpinned, per-window detection flaps on code-switched speech and the decoder emits fluent, confident text in the wrong language.
  • Speakers — how many, plus names and roles.
  • Domain vocabulary — product names, people, companies, jargon, currencies.

Done when you can state the language code, the speaker count, and at least five domain terms.

2. Transcribe

python scripts/transcribe.py AUDIO... --out DIR --language <code> --diarize --keyterms "term,term,..."

--provider selects the backend; auto takes the first with a key present. Setup, capability and cost per provider: references/providers.md.

Prefer a backend that diarizes. Speaker labels you derive yourself by reasoning about who-said-what are inference, and inference is a break in the chain of custody.

Done when every input file has a .json and .txt in DIR.

3. Audit before you read

python scripts/audit.py DIR

Two findings, both of which vanish once a transcript is flattened into prose:

  • Gaps — a recorder stopped mid-meeting drops content in silence, and the notes that follow read as complete. A gap is a stretch of the meeting you hold no evidence for.
  • Risky spans — numbers and proper nouns resting on low-confidence audio. This is where laundering happens.

Give every finding one of three dispositions: corroborated against a second transcript, confirmed with the user, or carried into the notes as a marked uncertainty.

Read the full file on GitHub · 69 lines

Files

What ships with it

5 files 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.

Changes

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.

  1. 2d ago First seen · 69 lines · 50 tokens per session scan A 45eab86fa713

Subscribe to this mod's changes

scribe is a skill published in the GitHub repository ooiyeefei/ccc (483 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 779 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens