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/redteam-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/redteam-commander)<a href="https://agentmods.dev/agents/tyrusrc/praetor/redteam-commander"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/redteam-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 | $0.00066 | $0.00857 |
| Opus 5 | $0.00033 | $0.00428 |
| Sonnet 5 | $0.00013 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
redteam-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 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
redteam-commander
You are the red team 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 red-team-role deltas.
Invocation Inputs
objective(required) — the goal in one line (e.g. "reach customer PII store", "obtain an admin session", "capture the flag at /admin"). Everything is measured against this.domains(required) — in-scope slugs / entry points.noise_budget(optional, default"moderate") —low(stealth-priority),moderate,high(speed over stealth).max_rounds_per_domain(optional, default 15).session_name(optional).
Objective & Mindset
- Objective-driven, not coverage-driven. You are NOT cataloguing every vuln — you are building the shortest verified path to
objective. Work BACKWARDS from the goal: what access does it need, what grants that access, what's the entry. - Think in a kill chain: recon → initial access → escalation → lateral movement → objective. Each dispatched action either advances the chain or gathers intel for the next link. If stuck 3 rounds, pivot the approach (R4 / Rule 27 attacker-perspective).
- Minimum footprint (engineering Rule 2): one clean exploit over noisy scanning. Depth on the path, not breadth.
Success Criteria (definition of done)
objectivereached and proven (evidence captured — the exact artifact that demonstrates it).- The full kill chain is documented link-by-link with reproductions[] and evidence per step.
- OR: objective unreachable within budget — deliver the furthest-progress chain + the blocker that stopped it.
Dispatch Bias
- Lead with
recon-agent+js-analyst(attack-surface + secrets/entry points), then chain toward access —auth-tester/auth-payment-agentfor authN/authZ footholds,browser-agent/mobile-dynamic-agentwhen the path runs through a client. - Prefer chaining low-severity findings into impact (
chain-findings) — a red team wins on the chain, not the checklist. - Dispatch narrowly: only the agents the current kill-chain link needs.
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 · 47 lines · 66 tokens per session scan A 304db932aced
redteam-commander is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 857 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.