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/bendrucker/claude/activitynpx skills add bendrucker/claude --skill activitygit clone --depth 1 https://github.com/bendrucker/claudeWhat 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 | $0.00070 | $0.01008 |
| Opus 5 | $0.00035 | $0.00504 |
| Sonnet 5 | $0.00014 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
activitywatch:activity 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activity
Report how the device was actually used, from ActivityWatch's local capture. This skill only reads. It never writes to the db.
ActivityWatch runs aw-server-rust in the background (a LaunchAgent supervises it via aw-qt). It records the focused app and window title (aw-watcher-window) and active vs idle spans (aw-watcher-afk) into a SQLite db. DuckDB attaches that db read-only, which is safe while aw-server holds its own write connection.
Database
~/Library/Application Support/activitywatch/aw-server-rust/sqlite.db
Override with AW_DB (the wrapper resolves it, since DuckDB cannot expand ~ in ATTACH). If the file is missing, ActivityWatch is not installed or has not captured yet.
Querying
Run a named query with scripts/aw-query.sh. Each query supports --recent <duration> (12h, 1d, 7d, 4w) to scope to a recent window, and -n <limit> to cap rows.
${CLAUDE_SKILL_DIR}/scripts/aw-query.sh top-apps
${CLAUDE_SKILL_DIR}/scripts/aw-query.sh top-apps --recent 1d
${CLAUDE_SKILL_DIR}/scripts/aw-query.sh window-titles --recent 7d -n 40
${CLAUDE_SKILL_DIR}/scripts/aw-query.sh afk --recent 1d
The aggregate queries (top-apps, window-titles, afk) return durations both formatted (duration, e.g. 1h 23m) and raw (seconds) so results are readable and still sortable/summable. app-timeline lists individual focus events and returns raw seconds only.
Queries
- top-apps — total focused time per app, most first. The headline "what did I use" answer.
- window-titles — time per window title within each app. What you were actually doing, not just which app was open. Needs Accessibility granted to ActivityWatch.
- app-timeline — focus events in reverse-chronological order (when you switched to what, for how long). Pair with
--recent 1dto reconstruct a day. - afk — active (
not-afk) vs idle (afk) time. How much of the window was actually at the keyboard.
Schema
Two tables in the attached aw database:
What ships with it
5 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 · 64 lines · 70 tokens per session scan A cb5331f9e2c9
activitywatch:activity is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 1,008 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 2026-08-30.
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.