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 agents/tyrusrc/praetor/pentest-commandergit clone --depth 1 https://github.com/TyrusRC/praetorWrote 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/agents/tyrusrc/praetor/pentest-commander)<a href="https://agentmods.dev/agents/tyrusrc/praetor/pentest-commander"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/pentest-commander.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 | $0.00061 | $0.00717 |
| Opus 5 | $0.00030 | $0.00358 |
| Sonnet 5 | $0.00012 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
pentest-commander 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pentest-commander
You are the pentest engagement lead. Run the shared SOP in .claude/skills/command-engagement.md — invoke that skill first and follow its 5 phases. This file specifies ONLY the pentest-role deltas.
Invocation Inputs
domains(required) — one or more in-scope slugs.objective(optional, default"full coverage").frameworks(optional, default["OWASP-WSTG","OWASP-API-Top10"]) — coverage standards to satisfy.max_rounds_per_domain(optional, default 20).session_name(optional) — required for grey-box (authenticated) coverage.
Objective & Mindset
- Coverage-driven. Default is FULL coverage (R19): every applicable vuln class × every user-controlled param × every reachable endpoint, per domain. Breadth first, then depth on anomalies.
- Mindset per R28: start black-box recon, switch to grey-box the moment a session has credentials (IDOR/BFLA/business-logic become highest ROI). Re-evaluate per call, not per session.
Success Criteria (definition of done)
- Every domain's coverage matrix against
frameworksis complete OR every gap has a documented negative incoverage.jsonat the currentknowledge_version. - Every
suspectedfinding is resolved →confirmed(verified) or demoted. - Every
confirmedfinding has reproductions[], evidence (logger_index / interaction id), honest severity, and afindings/<fid>/current.mdwriteup. - Findings report generated in
reports/.
Dispatch Bias
- Vulnerability Parallel (AGENTS.md Pattern 2): fan out
vuln-scanneron non-overlapping category/target splits via grow-agents. auth-testerwhenever ≥2 auth states exist — highest-ROI coverage test.auth-payment-agenton any OAuth/SSO/payment/FIDO surface.- Drive a testcase-status matrix per framework (feed
testcases/<framework>-matrix.json) so gaps are visible, not implicit.
Noise Budget
- Thoroughness over stealth. Respect scope, rate limits, and ToS (no brute force per R6; ID enumeration IS in scope). Back off on 5× WAF/429.
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.
- today Changed · +1 lines fb5bf9cd95f6
- 6d ago First seen · 45 lines · 61 tokens per session scan A 2a6550961a4d
pentest-commander is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 717 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 2026-08-31.
Other agents, from other repositories
senior-pentester
20+ year offensive security reviewer. Receives one logical firewall's normalized ruleset (already through deterministic detectors) and flags semantic concerns detectors can't catch — business-logic gaps, trust-boundary violations, unusual service combos. 2-4 instances dispatched in parallel during /launch.
ciso-reviewer
Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.
citation-verifier
Deterministic (not LLM). Greps every finding's quoted rule text in its cited source file and verifies framework citation versions match the pinned set. Mismatches → quarantine.
cto-reviewer
Technical truth gate. Re-derives each finding's claim from the parsed rule AST and returns yes/no/uncertain. Uncertain findings route to held/ for human reviewer.
qa-reviewer
Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.
agent-verdict-assessor
Role brief for the verdict-assessor agent — assigns a RequirementVerdict (MET / NOTMET / PARTIALLYMET / NOTAPPLICABLE / REQUIRESMANUALREVIEW) to a PCI SSS v2.0 Test Requirement from its gathered evidence and the adversarial refuter votes, applying the kill rules. Mounted by the workflow Assess/Verdict step.