classify

A proposal tool that reviews a recent conversation and suggests trackable work items. A work item is a recorded task or feature that can be reviewed before being added to the project's work log.

In plain words
What is it for?
Use it to scan a conversation for untracked tasks, features, or other work and write suggested entries to .work/suggestions.jsonl when the classifier is enabled.
Why use it?
It helps catch commitments or follow-up work that were discussed but never recorded. It proposes items for review instead of adding them directly to the official log.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/spillwavesolutions/wiki_ticket_sdd/classify
Any agent
npx skills add SpillwaveSolutions/wiki_ticket_sdd --skill classify
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/wiki_ticket_sdd

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 657 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash bf70d7ffb2e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/skills/classify/SKILL.md · 56 lines

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_id fresh: python3 -c "import sys; sys.path.insert(0,'bin'); import ulid; print(ulid.new())"
  • Dedupe FIRST: check the current bin/worklog fold titles AND prior unconsumed suggestions already in .work/suggestions.jsonl. Never re-propose an item that exists or was already suggested; record what you checked in dedupe_against.
  • Read classifier.min_confidence from .work/config.yml (default 0.7). If confidence < min_confidence, proposed.kind MUST be "triage" and the doubt goes in open_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 their open_questions to the user as questions, not items.
  • Rejected suggestions: mark consumed by appending {"consumed": true, "suggestion_id": "..."} to .work/suggestions.jsonl.

Read the full file on GitHub · 56 lines

Changes

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.

  1. 2d ago First seen · 56 lines · 52 tokens per session scan A bf70d7ffb2e1

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens