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/spillwavesolutions/wiki_ticket_sdd/classifynpx skills add SpillwaveSolutions/wiki_ticket_sdd --skill classifygit clone --depth 1 https://github.com/SpillwaveSolutions/wiki_ticket_sddWhat 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 | $0.00052 | $0.00657 |
| Opus 5 | $0.00026 | $0.00329 |
| Sonnet 5 | $0.00010 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
classify 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Classify — propose work items from conversation
Flag-gated (spec §6): meaningful only when classifier.enabled: true in
.work/config.yml. Propose, don't dispose — suggestions go to
.work/suggestions.jsonl (gitignored, per-clone, append-only); nothing enters
the event log until the main loop or the human promotes.
1. Spawn ONE background subagent
Spawn a single background subagent (never more than one) with this prompt:
Analyze the recent exchange for trackable work that has no work item yet. For each plausible item, append ONE JSON line to
.work/suggestions.jsonl:{"suggestion_id": "<ULID>", "source_span": "<turn or transcript ref>", "proposed": {"level": "task", "kind": "feature", "parent": null, "milestone": null, "title": "..."}, "confidence": 0.82, "open_questions": [], "dedupe_against": ["<item ULIDs checked>"]}
- Mint each
suggestion_idfresh:python3 -c "import sys; sys.path.insert(0,'bin'); import ulid; print(ulid.new())"- Dedupe FIRST: check the current
bin/worklog foldtitles AND prior unconsumed suggestions already in.work/suggestions.jsonl. Never re-propose an item that exists or was already suggested; record what you checked indedupe_against.- Read
classifier.min_confidencefrom.work/config.yml(default 0.7). If confidence < min_confidence,proposed.kindMUST be"triage"and the doubt goes inopen_questions— never a confident guess on a load-bearing field.- NEVER append to
.work/todo.jsonl,.work/done.jsonl, or any event log. Suggestions only.- NEVER ask the user anything — you cannot block. Write suggestions and exit.
2. Dispose next turn (main loop)
Next turn, read .work/suggestions.jsonl, skipping records already marked
consumed:
- High-confidence suggestions: offer them for promotion —
bin/worklog promote <suggestion-id>creates the real item. - Low-confidence (
kind:triage) suggestions: surface theiropen_questionsto the user as questions, not items. - Rejected suggestions: mark consumed by appending
{"consumed": true, "suggestion_id": "..."}to.work/suggestions.jsonl.
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 · 56 lines · 52 tokens per session scan A bf70d7ffb2e1
classify is a skill published in the GitHub repository SpillwaveSolutions/wiki_ticket_sdd (10 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 657 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…