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/knopki/agent-skills/donsetch-clinpx skills add knopki/agent-skills --skill donsetch-cligit clone --depth 1 https://github.com/knopki/agent-skillsWhat 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 | $0.00069 | $0.02566 |
| Opus 5 | $0.00034 | $0.01283 |
| Sonnet 5 | $0.00014 | $0.00513 |
| Haiku 4.5 | $0.00007 | $0.00257 |
Grade A, and why
donsetch-cli 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
donsetch CLI
Overview
Drive the donsetch CLI to do web research for an agent: search, fetch, and
crawl. Each command returns clean markdown plus a machine-readable JSON
envelope (--json), token-efficient by default, with bot-wall/PDF handling
built in.
Assume installed, otherwise: npm install -g donsetch or ask user to install.
When to Use
Trigger this skill when live web content is needed:
- The user asks to search the web, look something up online, or get current information beyond the model's training data.
- A specific URL must be read as clean markdown (incl. pages behind a bot-wall or JS shell, or a PDF).
- A whole site or docs subsite must be extracted into markdown.
- Token cost matters and only the relevant blocks of a long page are wanted.
Do not trigger this skill for:
- Code search across public GitHub repos — use the
grep-app-cliskill (literal source matching, not web search). - Reading files already on the local filesystem — use
read.
Decision: which command?
| Need | Command |
|---|---|
| Discover what to read (find URLs) | donsetch search |
| Read one specific URL | donsetch fetch |
| Read a long docs page efficiently | fetch --toc, then --section or --focus |
| Extract a multi-page site/docs | donsetch crawl |
| See a site's URL inventory before fetching | crawl --mode map |
Sitemap missing or map returned empty |
crawl --mode content |
| A crawl stopped on budget/deadline | crawl --resume <token> |
Pipeline: search → pick best URLs → fetch (or crawl for many pages).
donsetch search — find URLs
donsetch search rust async trait dyn dispatch
donsetch search "exact phrase" --intent code --max-results 10
donsetch search site:github.com tokio
--max-results(default 7, max 12). The top 7 almost always suffice; raise only when results are weak.--intentauto|web|code|paper|news|entity.autodetects from the query and adds verticals:code→ GitHub/HN/StackExchange/MDN,paper→ Scholar/arXiv,news→ Google News/HN,entity→ Wikipedia.--jsonfor the full envelope;-qto silence the stderr stats line.
What ships with it
1 file 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 · 207 lines · 69 tokens per session scan A c4df01d55ce7
donsetch-cli is a skill published in the GitHub repository knopki/agent-skills (2 stars, last pushed 18d ago), licensed MIT. It adds 69 tokens to every session and 2,566 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…