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.
git 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/commands/nebulae/trudi/trudi-stop-watcher)<a href="https://agentmods.dev/commands/nebulae/trudi/trudi-stop-watcher"><img src="https://agentmods.dev/badge/commands/nebulae/trudi/trudi-stop-watcher.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 5.1 | $0.00023 | $0.00501 |
| Opus 5 | $0.00012 | $0.00251 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
trudi-stop-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 8d 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
/trudi-stop-watcher
Stops the live-monitoring watcher sidecar(s) for a case: SIGTERMs the
detached trudi-velo-watcher.py process(es) and removes the
Custom.TRUDI.* artifacts from the client event table so no new alerts
are drained.
The argument, if supplied, names the case. Otherwise read it from
~/cases/.common/active_case.
Steps
1. Resolve the case
case_id = $ARGUMENTS if non-empty, else cat ~/cases/.common/active_case.
Refuse if neither is set.
2. Ensure an execution log is active (gate prerequisite)
If core.execution_log.log._path is unset, call
misc.start_execution_log(case_id, output_path="~/cases/<case_id>/analysis/<case_id>_trace.json")
so monitor.* calls pass the DAIR cold-start gate.
3. Enumerate watchers
monitor.list_watchers(case_id)
Each record carries the client_id, alive/dead state, uptime, and alert
count. If none are alive, print "No live watchers for <case_id>." and
exit (nothing to stop).
4. Stop each alive watcher
For every watcher reported alive:
monitor.stop_watcher(client_id=<from the record>, case_id=case_id)
The response reports killed_pid, whether the stop was graceful, and
event_table_cleared. If a pid_file lingers for an already-dead
process, note it (it's harmless; start_watcher overwrites it).
5. Report
List each stopped watcher: client_id, killed pid, graceful/forced,
event-table-cleared. State that no further alerts will be drained until
/trudi-start-watcher is run again.
Notes
- Stopping the watcher does not clear already-drained alerts,
investigation traces, or response suggestions — use
/trudi-clear-casefor that. - The victim host itself is untouched — this only stops TRUDI's collection of its events.
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.
- 8d ago First seen · 55 lines · 23 tokens per session scan A f74aae6b55b5
trudi-stop-watcher is a command published in the GitHub repository nebulae/trudi (57 stars, last pushed 7d ago), licensed MIT. It adds 23 tokens to every session and 501 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.