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/zhaohb/deskmate/appsnpx skills add zhaohb/deskmate --skill appsgit clone --depth 1 https://github.com/zhaohb/deskmateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhaohb/deskmate/apps)<a href="https://agentmods.dev/skills/zhaohb/deskmate/apps"><img src="https://agentmods.dev/badge/skills/zhaohb/deskmate/apps.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01620 |
| Opus 5 | $0.00000 | $0.00810 |
| Sonnet 5 | $0.00000 | $0.00324 |
| Haiku 4.5 | $0.00000 | $0.00162 |
Grade A, and why
apps 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 4d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeskMate skill
You are an AI agent with access to deskmate, a local screen and audio recorder. You can query the user's recent screen activity, audio transcriptions, and UI events through the local REST API.
API base
Available tools
You have the following tools (invoke via tool_calls in agent mode, or HTTP as documented).
activity_summary tool (call first for day recap)
Same as GET /activity-summary below. In agent mode, call the activity_summary tool with start_time and end_time from Context before writing a recap.
activity-summary (preferred for broad overviews)
Aggregated bundle for day recap / habits. Returns apps with minutes, windows/tabs, key_texts (OCR + typed input), edited_files, audio_summary, snippets, optional memories, recording health, and guidance.
GET /activity-summary?start_time=<ISO8601>&end_time=<ISO8601>
Response shape (key fields):
{
"apps": [{"name": "Cursor.exe", "minutes": 42.5, "frame_count": N, "first_seen": "...", "last_seen": "..."}],
"windows": [{"app_name": "...", "window_name": "...", "minutes": N, "browser_url": "..."}],
"key_texts": [{"text": "...", "app_name": "...", "window_name": "...", "timestamp": "..."}],
"edited_files": [{"path": "c:/proj/file.md", "frame_count": N}],
"audio_summary": {"segment_count": N, "speakers": [...], "top_transcriptions": [...]},
"snippets": [{"source": "screen|audio", "text": "...", "timestamp": "..."}],
"data_status": "ok|no_capture_in_range|not_recording|empty_but_recording",
"guidance": {"next_best_query": "..."}
}
Do not use raw title_change UI events for narratives — use key_texts, snippets, and OCR.
search (for targeted queries)
Search screen captures (OCR text, accessibility text) and audio transcriptions.
GET /search?limit=20&content_type=all&start_time=<ISO8601>&end_time=<ISO8601>
Query parameters:
- q: text search query (optional for OCR; required for audio/UI)
- content_type: "all" | "ocr" | "audio" | "ui"
- limit: max results (default 20)
- offset: pagination offset
- start_time / end_time: ISO 8601 timestamps
- app_name: filter by app (e.g. "chrome.exe", "Cursor.exe")
- window_name: filter by window title
- min_length / max_length: filter by text length
- speaker_ids: filter audio by speaker IDs (comma-separated)
What ships with it
32 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.
- __init__.py 0 B runs code
- agent.py 180 KB runs code
- ai-habits/app.py 1.3 KB runs code
- ai-habits/pipe.md 877 B
- ai-prompt-journal/app.py 16 KB runs code
- ai-prompt-journal/pipe.md 6.2 KB
- common.py 5.5 KB runs code
- day-recap/app.py 2.2 KB runs code
- day-recap/pipe.md 837 B
- email-compose/app.py 9.6 KB runs code
- email-compose/pipe.md 1.9 KB
- email-digest/app.py 1.6 KB runs code
- email-digest/pipe.md 2.3 KB
- habit-report/app.py 1.6 KB runs code
- habit-report/pipe.md 1.7 KB
- learning_evidence.py 17 KB runs code
- learning_slice.py 48 KB runs code
- meeting-summary/app.py 1.8 KB runs code
- meeting-summary/pipe.md 1.9 KB
- README.md 15 KB
- standup-update/app.py 1.3 KB runs code
- standup-update/pipe.md 1.1 KB
- time-breakdown/app.py 1.3 KB runs code
- time-breakdown/pipe.md 1.6 KB
- todo-list/app.py 10.0 KB runs code
- todo-list/pipe.md 4.0 KB
- user-learning/app.py 3.3 KB runs code
- user-learning/pipe.md 8.0 KB
- user-profile/app.py 1.7 KB runs code
- user-profile/pipe.md 1.6 KB
- video-export/app.py 2.1 KB runs code
- video-export/pipe.md 484 B
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.
- 4d ago First seen · 141 lines · 0 tokens per session scan A 4d8ef0c1509c
apps is a skill published in the GitHub repository zhaohb/deskmate (113 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,620 tokens. 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.
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…