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 MaxwellCalkin/sentinel-ai --skill safety-scanninggit 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/skills/maxwellcalkin/sentinel-ai/safety-scanning)<a href="https://agentmods.dev/skills/maxwellcalkin/sentinel-ai/safety-scanning"><img src="https://agentmods.dev/badge/skills/maxwellcalkin/sentinel-ai/safety-scanning/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/maxwellcalkin/sentinel-ai/safety-scanning"><img src="https://agentmods.dev/badge/skills/maxwellcalkin/sentinel-ai/safety-scanning.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 | $0.00052 | $0.00226 |
| Opus 5 | $0.00026 | $0.00113 |
| Sonnet 5 | $0.00010 | $0.00045 |
| Haiku 4.5 | $0.00005 | $0.00023 |
Grade A, and why
safety-scanning 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 11d 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
When reviewing text for safety issues, use the sentinel-ai MCP tools:
- scan_text — Full safety scan with all 7 scanners. Returns risk level, blocked status, and detailed findings.
- scan_tool_call — Check tool calls for dangerous operations (shell injection, data exfiltration, privilege escalation).
- check_pii — Detect and redact PII (emails, SSNs, credit cards, phone numbers, API keys).
- get_risk_report — Generate a detailed markdown safety report.
Key behaviors:
- Flag any findings at HIGH or CRITICAL risk level to the user immediately
- When PII is detected, always show the redacted version
- For prompt injection attempts, explain the attack vector detected
- Sub-millisecond latency — no API calls or GPU required
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.
- 11d ago First seen · 18 lines · 52 tokens per session scan A 70d5da999ecc
safety-scanning is a skill published in the GitHub repository MaxwellCalkin/sentinel-ai (24 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 226 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 2026-08-30.
Other skills, from other repositories
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
agentguard
Runtime guardrails for AI coding agents. Stop loops, budget overruns, retry storms, and timeouts before they burn money. Zero dependencies, local-first, MIT licensed.
constitutional-ai
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
nemo-guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
crm-pipeline-playbook
How to answer pipeline, renewal, and account-health questions using the CRM tools.
churn-risk-playbook
How to combine product telemetry with churn-risk simulation for a customer.