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/8nobletruths/sabba/pentestgit clone --depth 1 https://github.com/8NobleTruths/sabbaWrote 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/8nobletruths/sabba/pentest)<a href="https://agentmods.dev/commands/8nobletruths/sabba/pentest"><img src="https://agentmods.dev/badge/commands/8nobletruths/sabba/pentest.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00259 |
| Opus 5 | $0.00008 | $0.00130 |
| Sonnet 5 | $0.00003 | $0.00052 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
pentest 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 6d 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
Run an authorized security assessment of: $ARGUMENTS
Use the sabba MCP tools. Only ever act on targets that are in scope -- kali_run refuses an
out-of-scope target, and you must not try to work around that.
- Call
list_security_toolsto see what recon and scanning tools are installed. - Recon:
kali_runnmap with-oX -against the target to get open ports and services. - If a web service is exposed:
kali_runnuclei (-jsonl), httpx (-json), and ffuf when fuzzing a path or vhost. - Do not trust a scanner's output. Treat every hit as a candidate and confirm the ones that
matter with
verifyorhuntbefore you report them. - Report only what you could confirm, each with its evidence. Be explicit about what is unconfirmed.
If kali_run blocks a target as out of scope, stop and tell the operator to add it to
SABBA_SCOPE; never bypass the scope check.
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.
- 6d ago First seen · 20 lines · 16 tokens per session scan A 7ae681c256ea
pentest is a command published in the GitHub repository 8NobleTruths/sabba (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 259 once invoked, about $0.0001 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 commands, from other repositories
bob-evaluate
Run or resume a Hacker Bob security evaluation.
bob-egress
Manage Hacker Bob egress profiles for this project.
bob-update
Run the installed Hacker Bob update workflow for this project.
bob-export
Create a Hacker Bob post-release improvement bundle for the currently installed Bob version.
security-semgrep-setup
Check if Semgrep is installed and working. If not, install it using the best available method. Then log in to Semgrep Pro, enable the Pro engine, and run a local Pro scan in the current directory.
sessions
List all Claude Code sessions across all projects, sorted by most recent. Show project context, date, and the exact resume command for each session.