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 agentmods add commands/clear-capabilities/agentic-security/scangit clone --depth 1 https://github.com/Clear-Capabilities/agentic-securityWhat 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 | $0.00025 | $0.04604 |
| Opus 5 | $0.00013 | $0.02302 |
| Sonnet 5 | $0.00005 | $0.00921 |
| Haiku 4.5 | $0.00003 | $0.00460 |
Grade C, and why
scan scanned grade C with 2 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 yesterday.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
**`/scan --mcp`** — Audit MCP server configs (`claude_desktop_config.json`, `.mcp.json`, `mcp_servers.json`). Covers: untrusted install vectors (`curl | sh`), hardcoded API keys in `env:` blocks, prompt-injection in serv Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**`/scan --mcp`** — Audit MCP server configs (`claude_desktop_config.json`, `.mcp.json`, `mcp_servers.json`). Covers: untrusted install vectors (`curl | sh`), hardcoded API keys in `env:` blocks, prompt-injection in serv The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 268 lines · 25 tokens per session scan C 9892fda49813
scan is a command published in the GitHub repository Clear-Capabilities/agentic-security (87 stars, last pushed 3d ago), with no licence file. It adds 25 tokens to every session and 4,604 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
continue
Resume a paused dev workflow, or take over a cloud session from another machine.
create
Create a new workflow suite (published to hub by default), or edit an existing one with --flow=.
interrupt
Pause the active dev workflow loop without clearing state — resume later with /stagent:continue.
publish
Publish a local workflow directory to the cloud workflow hub.
start
Start the dev workflow — inline planning, then autonomous execute→verify→review→QA loop.
login
Sign in to the stagent cloud server.