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 agentmods add skills/nweii/agent-stuff/enrich-from-transcriptnpx skills add nweii/agent-stuff --skill enrich-from-transcriptgit 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/enrich-from-transcript)<a href="https://agentmods.dev/skills/nweii/agent-stuff/enrich-from-transcript"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/enrich-from-transcript.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01595 |
| Opus 5 | $0.00028 | $0.00797 |
| Sonnet 5 | $0.00011 | $0.00319 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
enrich-from-transcript 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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enrich from transcript
Two modes, decided from how the user invoked the skill and what they pointed you at:
- Enrich mode — there's an existing note (often an AI-summary version) and a transcript. Add depth without overwriting what's there.
- Scaffold mode — there's only a transcript. Build a new note from scratch.
If both an existing note and a transcript are referenced, default to enrich mode. If unclear, ask.
1. Read the whole transcript first
Read it end to end before writing anything. Skimming misses repeated phrasings, hesitations, and asides, which often matter most.
If there's an existing note, read it too so the enrichment complements rather than duplicates it.
Auto-generated transcripts (i.e., from Whisper, Granola, Otter, etc.) may contain mistranscription errors. Don't quote, bold, or read significance into phrases that look garbled or contain weird word choices that may be transcription artifacts. Flag clearly corrupted passages rather than building interpretation around them. If the transcript needs systematic cleanup, treat that as separate work and surface it to the user rather than mixing it into enrichment.
2. Apply the six dimensions
Work through these as you read. Not every transcript will yield every dimension — surface what's actually there, do not pad to fill all six.
Whenever your interpretation hinges on something specific in the transcript — a phrase you'd quote verbatim, a number or name, an unusual word choice that seems significant — the auto-transcription may be wrong. Verify against surrounding context before building interpretation around it, and when in doubt, flag rather than interpret confidently.
Granular narrative detail
Capture the reasoning, examples, and stories shared in the transcript, rather than summarizing them. If someone explained their pricing approach by walking through three customer profiles, write the three profiles, not "we discussed pricing."
A useful check: could the user recall the substance from your notes alone, or would they need to revisit the transcript?
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.
- 4d ago First seen · 111 lines · 57 tokens per session scan A 1e222028f000
enrich-from-transcript is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 16d ago), licensed MIT. It adds 57 tokens to every session and 1,595 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…