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 skills add nebulae/trudi --skill trudi-start-watchergit clone --depth 1 https://github.com/nebulae/trudiWrote 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/nebulae/trudi/trudi-start-watcher)<a href="https://agentmods.dev/skills/nebulae/trudi/trudi-start-watcher"><img src="https://agentmods.dev/badge/skills/nebulae/trudi/trudi-start-watcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nebulae/trudi/trudi-start-watcher"><img src="https://agentmods.dev/badge/skills/nebulae/trudi/trudi-start-watcher.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00030 | $0.00380 |
| Opus 5.5 | $0.00012 | $0.00152 |
| Sonnet 5.5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
trudi-start-watcher 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.
What it actually says
Resolve the explicitly named case, otherwise use the current case directory's
CLAUDE.md. Use the shared active_case file only if neither identifies a case.
Read that case's instructions and monitoring/config.json. Use actual
trudi-sift MCP tools; the dotted names here describe their namespaces.
Initialize the case execution log through misc.start_execution_log only if none is active. Preserve existing traces. If an investigation is open, resume it with monitor.start_investigation rather than redirecting its trace.
Call monitor.list_watchers. Reuse an already-running producer for the case; do not stop it merely to make the setup command succeed.
For a case with cef_ingest configuration, start monitor.start_cef_ingest if it isn't running. Confirm its configured signed sender, source-client binding, and decoy endpoint. Raw UDP is collection-only. A pure external-detection case such as WINDECOY-DEMO does not need another host-detector subscription. Its response source still needs an existing baseline for the current client.
For a host-detector case, resolve the current client using velo.list_clients, preferring the most recent matching hostname. Reuse its baseline. Capture a missing baseline only when the host is known clean; never absorb current attack artifacts to satisfy a setup prerequisite. Start monitor.start_watcher with the case's intended detectors; surface every returned warning.
Confirm the producer is alive and report its client ID, PID, signing posture, and dashboard URL. Do not start an attack, acknowledge alerts, or weaken response policy. Use $trudi-watch-alerts when the operator wants the analyst loop running; obey an explicit exercise hold.
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 · 34 lines · 30 tokens per session scan A 1d45c7ef3a2a
trudi-start-watcher is a skill published in the GitHub repository nebulae/trudi (67 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 380 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…