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-check-alerts)<a href="https://agentmods.dev/commands/nebulae/trudi/trudi-check-alerts"><img src="https://agentmods.dev/badge/commands/nebulae/trudi/trudi-check-alerts/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/commands/nebulae/trudi/trudi-check-alerts"><img src="https://agentmods.dev/badge/commands/nebulae/trudi/trudi-check-alerts.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 | $0.00017 | $0.06843 |
| Opus 5.5 | $0.00007 | $0.02737 |
| Sonnet 5.5 | $0.00003 | $0.01369 |
| Haiku 4.5 | $0.00002 | $0.00684 |
Grade A, and why
trudi-check-alerts 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 — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/trudi-check-alerts
Polls the active TRUDI live-monitoring case for new alerts and runs
one investigation per /loop tick over the entire bundle of alerts
drained in that tick. Designed to be called on a fixed interval via
/loop 15s /trudi-check-alerts so anomalies are investigated within
~30s of firing on the victim host.
The argument, if supplied, names the case. Otherwise read it from
~/cases/.common/active_case.
Response ordering — contain → eradicate → investigate-for-record
Both response actions are fast and up front; the forensic write-up trails and never blocks them:
- Contain first (step 4). The moment a high-confidence alert is in hand —
before any
reason.*/dair_assesscall — snapshot the volatile evidence (read-only, ~seconds) and auto-execute the reversible, low-risk containment (e.g. block the egress channel). AUTO tier: no approval, no finding. - Offer eradication right after (step 5). For a confirmed-positive alert
class, resolve the kill target with ONE fast pivot (or take the
pid/image_paththe bundle already carries) and immediately queue the destructive action for operator approval (a popup). This is seconds after containment — it waits only on target resolution, NOT on the finding/report ceremony. (The earlier design put eradication after the full investigation; a real run then contained in ~1s but never offered the kill, because the finding ceremony ran ~24 min and never finished. Don't repeat that.) - Then the full investigation + report (step 6). hypothesize → DAIR → findings → report, for the court-record, running after the response is already in flight. If it unexpectedly clears the alerts as benign, revert the step-4 containment and drop any still-queued eradication.
Containment is reversible so it runs on its own; eradication is irreversible so it is operator-approved — but both fire within seconds, gated only on a confirmed-positive alert plus a resolved target, never on the paperwork.
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 Changed · +234 lines 4fbcba5bbd4d
- 1mo ago Changed a82da2339b30
- 2mo ago First seen · 277 lines · 17 tokens per session scan A adf80370775c
trudi-check-alerts is a command published in the GitHub repository nebulae/trudi (67 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 6,843 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 2026-08-30.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.