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/MaxwellCalkin/sentinel-aiWrote 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/maxwellcalkin/sentinel-ai/check-safety)<a href="https://agentmods.dev/commands/maxwellcalkin/sentinel-ai/check-safety"><img src="https://agentmods.dev/badge/commands/maxwellcalkin/sentinel-ai/check-safety/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/maxwellcalkin/sentinel-ai/check-safety"><img src="https://agentmods.dev/badge/commands/maxwellcalkin/sentinel-ai/check-safety.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 | $0.00000 | $0.00169 |
| Opus 5 | $0.00000 | $0.00084 |
| Sonnet 5 | $0.00000 | $0.00034 |
| Haiku 4.5 | $0.00000 | $0.00017 |
Grade A, and why
check-safety 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 10d 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
/check-safety — Generate a safety risk report
Generate a detailed safety risk report for the current conversation or a specific file.
Usage
/check-safety [file path or text]
Behavior
Use the Sentinel AI get_risk_report MCP tool to generate a comprehensive safety analysis:
- If a file path is provided, read the file and scan its contents
- If text is provided, scan that text directly
- If nothing is provided, scan the most recent assistant response in the conversation
Present the report showing:
- Overall risk level
- Whether content would be blocked
- Findings grouped by category (prompt_injection, pii, harmful_content, toxicity, hallucination)
- Specific findings with risk levels
- Redacted text if PII was found
Input
$ARGUMENTS
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.
- 10d ago First seen · 26 lines · 0 tokens per session scan A 4b93ef3034c3
check-safety is a command published in the GitHub repository MaxwellCalkin/sentinel-ai (24 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 169 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 commands, from other repositories
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
show-lessons
Display promoted lessons and their corrective actions.
staleness-check
Check what governance artifacts went stale based on what was edited this session.
check-drift
Run schema drift detection — compare the live Postgres schema against ORM table definitions, backend function .select() calls, the schema doc, and the techstack inventory.
start
A Korean-language start command for beginning a repair loop after refining a goal, making a backup, giving guidance, and confirming the plan.