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/mupozg823/timecode-agent/skillnpx skills add mupozg823/timecode-agent --skill skillgit clone --depth 1 https://github.com/mupozg823/timecode-agentWhat 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 | $0.00113 | $0.03469 |
| Opus 5 | $0.00056 | $0.01734 |
| Sonnet 5 | $0.00023 | $0.00694 |
| Haiku 4.5 | $0.00011 | $0.00347 |
Grade A, and why
timecode-agent 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.
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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TIMECODE-AGENT
Hypothesize from the transcript first, verify only the uncertain moments visually, then persist the result as checkpoints. Never capture every frame; state the hypothesis each capture tests. Never promote a device- or dataset-local number into a universal rule.
References, read only when needed
| Situation | Reference |
|---|---|
| OCR, diarization, faces, scene false positives, precise visual checks | Verification toolbox |
| Highlight scoring, boundaries, beat-sync rhythm cut, montage grammar, reframe, NLE handoff | Output handoff |
| Resume, search, glossary, wiki, storage | Corpus lifecycle |
| Wiki labels, relations, narrative, queries | Wiki schema |
| Ingesting 3 or more videos | Batch contract |
| Harnesses other than Claude Code | Harness matrix |
| Install, backends, profiles, cache | Runtime setup |
Request to loop routing
Fold the user's words into a loop first. Step numbers come after.
| User says | Loop | Entry |
|---|---|---|
| new video, understand, analyze, "what is this" | Ingest (develop) then Kubrick (understand) | step 0: va ingest --signals, then va brief |
| highlight, shorts, "cut this" | Kubrick, then the cut workflow of Kuleshov (edit) | named span self-converges (step 4); open-ended waits for global convergence |
| "where was that scene", recall | Search | va search — never re-ingest |
| Premiere, editor handoff, markers | Bridge | va export in step 5 |
| listing, wiki, browser, external vault refresh | Archive (project knowledge) | va index, va wiki, va view, va bridge |
Pipeline: ingest (develop), search (recall), Kubrick (understand), Kuleshov (edit), cut (assemble), archive (preserve).
Kubrick writes the fact ledger (checkpoints.jsonl); Kuleshov writes the edit
decision ledger (sequences.jsonl). Kuleshov never modifies the fact
ledger. Correct a factual error in the checkpoint, then derive the edit again.
What ships with it
8 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.
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.
- 2d ago First seen · 285 lines · 113 tokens per session scan A 5490a94fd28c
timecode-agent is a skill published in the GitHub repository mupozg823/timecode-agent (53 stars, last pushed 26d ago), licensed MIT. It adds 113 tokens to every session and 3,469 once invoked, about $0.0006 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.
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.
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…
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.
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.