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/dfirs1car1o/sicario-specWrote 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/dfirs1car1o/sicario-spec/sicario.assess)<a href="https://agentmods.dev/commands/dfirs1car1o/sicario-spec/sicario.assess"><img src="https://agentmods.dev/badge/commands/dfirs1car1o/sicario-spec/sicario.assess/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/dfirs1car1o/sicario-spec/sicario.assess"><img src="https://agentmods.dev/badge/commands/dfirs1car1o/sicario-spec/sicario.assess.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 | $0.00086 |
| Opus 5 | $0.00000 | $0.00043 |
| Sonnet 5 | $0.00000 | $0.00017 |
| Haiku 4.5 | $0.00000 | $0.00009 |
Grade A, and why
sicario.assess 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 12d 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
/sicario.assess
Assess the repository against SicarioSpec guardrails.
Output:
generated/sicario/assessment.mdgenerated/sicario/gate-summary.json
Required checks:
- required spec/plan/task sections
- threat model presence
- docs impact presence
- diagram source presence
- hardcoded secret patterns
- AI-sensitive specs with prompt-injection/tool-boundary guardrails
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.
- 12d ago First seen · 19 lines · 0 tokens per session scan A 362fd3581cb8
sicario.assess is a command published in the GitHub repository dfirs1car1o/sicario-spec (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 86 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 2026-08-31.
Other commands, from other repositories
agt-status
Show the active AGT governance status for this Claude Code session.
web3-audit
Command "web3-audit" from Zyrexnn/Cybermes, covering /web3-audit, usage, step 0: pre-dive kill signals, find accounting variables and find all early returns in critical functions.
recon
Command "recon" from Zyrexnn/Cybermes, covering /recon, what this does, usage, steps and step 1: subdomain enumeration.
remember
Command "remember" from Zyrexnn/Cybermes, covering /remember, usage and what it is not.
assay-inventory
List installed Claude Code plugins, MCP servers, hooks, and settings overrides.
rfp
Vendor RFP questionnaire from the SAIL V2 catalog — security-vendor coverage questionnaire by default, platform-vendor framing on request.