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/tatargabor/set-copilot/transcript-recovernpx skills add tatargabor/set-copilot --skill transcript-recovergit clone --depth 1 https://github.com/tatargabor/set-copilotWrote 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/tatargabor/set-copilot/transcript-recover)<a href="https://agentmods.dev/skills/tatargabor/set-copilot/transcript-recover"><img src="https://agentmods.dev/badge/skills/tatargabor/set-copilot/transcript-recover.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 5.1 | $0.00028 | $0.01944 |
| Opus 5 | $0.00014 | $0.00972 |
| Sonnet 5 | $0.00006 | $0.00389 |
| Haiku 4.5 | $0.00003 | $0.00194 |
Grade A, and why
transcript-recover 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 yesterday.
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
transcript-recover — content recovery from recorded meetings
The mechanical half (stitching) is cheap and the engine does it. The expensive half is reading a whole meeting to find what was said that never reached the notes — that costs a model pass per transcript, and it must happen once per transcript, ever.
That is why this skill does not decide from memory what has been done. set-copilot recovery
holds the record, in the engine, written as a side effect of doing the work. Consult it first,
act only on what is pending, and deliver findings through it.
For the mechanical state faults instead — an orphaned PID, a capture that never handed its
transcript over, a stale wall claim — use /set-repair. It is cheap and safe to run often.
Phase 1 — discovery
Find candidate transcripts. Three places, and the third is the one that gets missed:
- Per-session runtime dirs:
.set/copilot/*/under the project. - The global runtime dir if this project ever ran without
SET_COPILOT_DIR(/tmp/set-copilot). - Hand-filed recordings. A recording saved by a human is usually not named
transcript*— a real one was2026-07-14-csakany-robi-copilot-raw-part1.jsonl. The directory scan only knows the capture's own naming convention, so a file like that needs an explicit glob:--input 'recordings/*.jsonl'.
Two things that look like transcripts and are not:
wall-events.jsonl— the wall's event log. Never a transcript.*-stitched.jsonl— this workflow's own output.
Phase 2 — what is actually pending
set-copilot recovery status --json # the project's runtime dirs
set-copilot recovery status --input '<dir-or-glob>' --json
Read pending.stitch, pending.review, artifactsOnly, dangling, staleStitch and
hookInstalled.
artifactsOnlyis stitched, but by an unknown version. The.mdand-stitched.jsonlare on disk with no ledger entry — that is every recording made before the ledger existed. Phase 3 restitches them (which is what puts them in the ledger); their review status is unaffected and is the one that decides whether the expensive read still has to happen.
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.
- yesterday First seen · 172 lines · 28 tokens per session scan A 48e79184de2a
transcript-recover is a skill published in the GitHub repository tatargabor/set-copilot (2 stars, last pushed 13d ago), licensed MIT. It adds 28 tokens to every session and 1,944 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…