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/mpaarating/ai-workflow-kit/watchlistnpx skills add mpaarating/ai-workflow-kit --skill watchlistgit clone --depth 1 https://github.com/mpaarating/ai-workflow-kitWhat 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 | $0.00015 | $0.00805 |
| Opus 5 | $0.00008 | $0.00402 |
| Sonnet 5 | $0.00003 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
watchlist 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watchlist
Track what you want to watch, rate what you've seen, and get suggestions based on your taste.
Trigger Phrases
- "want to watch"
- "add to watchlist"
- "watching [title]"
- "finished [title]"
- "rate [title]"
Workflow
Adding to watchlist
When the user mentions a movie or show they want to watch:
- Identify the title (and whether it's a movie or show)
- Ask for or infer genre tags: Action, Comedy, Drama, Horror, Sci-Fi, Documentary, Thriller, Animation, Romance
- Add to watchlist with status "To Watch"
- Confirm:
Added: "Severance" (Sci-Fi, Thriller) — To Watch
Marking as watched
When the user says they finished or watched something:
- Find the title in the watchlist
- Update status to "Watched" with today's date
- Ask for a rating (1-5) and optional one-line review
- If no rating given, prompt: "How was it? (1-5)"
- Confirm:
Updated: "Severance" — Watched (4/5) "Incredible world-building"
Rating
When the user rates something not yet in the list:
- Add it as "Watched" with the rating
- Accept optional review text
- Confirm the entry
Rating scale: 5 (loved it), 4 (really good), 3 (decent), 2 (disappointing), 1 (skip it)
Listing and suggestions
When asked "what should I watch" or "show my watchlist":
- Show unwatched items grouped by genre
- If the user mentions a mood, map it to genres and filter:
- "something light" → Comedy, Animation, Romance
- "something intense" → Thriller, Horror, Drama
- "something smart" → Sci-Fi, Documentary, Drama
- "something fun" → Action, Comedy, Animation
- Suggest 1-3 matching titles from their list
- If no matches or list is empty, offer to add something
Storage
Using {{notes}}: Store as a database with fields: Title, Type (Movie/Show), Genre, Status (To Watch/Watching/Watched), Rating, Review, Date Added, Date Watched.
Markdown fallback: Store in ~/.ai-workflow/watchlist.md:
## To Watch
- **Severance** (Show) — Sci-Fi, Thriller — Added Mar 19
## Watched
- **The Brutalist** (Movie) — Drama — 4/5 — "Ambitious and gorgeous" — Mar 15
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 · 109 lines · 15 tokens per session scan A 9bbf494ec6a5
watchlist is a skill published in the GitHub repository mpaarating/ai-workflow-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 805 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 2026-08-31.
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.
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.