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/Clear-Capabilities/agentic-securityWrote 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/clear-capabilities/agentic-security/setup)<a href="https://agentmods.dev/commands/clear-capabilities/agentic-security/setup"><img src="https://agentmods.dev/badge/commands/clear-capabilities/agentic-security/setup/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/clear-capabilities/agentic-security/setup"><img src="https://agentmods.dev/badge/commands/clear-capabilities/agentic-security/setup.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 | $0.00026 | $0.03606 |
| Opus 5.5 | $0.00010 | $0.01442 |
| Sonnet 5.5 | $0.00005 | $0.00721 |
| Haiku 4.5 | $0.00003 | $0.00361 |
Grade C, and why
setup scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `--destructive-guard` | Configure the destructive-Bash-command guard (rm -rf, force-push, etc.). Modes: `warn`, `block`, `off` | The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 1mo ago First seen · 260 lines · 26 tokens per session scan C c82edb992860
setup is a command published in the GitHub repository Clear-Capabilities/agentic-security (120 stars, last pushed today), with no licence file. It adds 26 tokens to every session and 3,606 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
ci-readout
Generate a comprehensive summary of recent CI runs and failing jobs.
quality-check
Execute a comprehensive quality gate check (lint, test, build, format) before allowing code to merge.
release-check
Run the complete release readiness pipeline (version checks, changelog, final quality gates) and assign a release confidence score.
devops
Author CI/CD, containers, or IaC following the repo's platform — deploy and secrets flagged for human approval, never executed.
release
Automates the release preparation and CI/CD handoff process.
ship
Puts approved code into production and closes the cycle. PR + CI + deploy + simplify + docs + cleanup. Use after /fractal:review approves.