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 instructions/tyrusrc/praetor/agents-mdgit 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/instructions/tyrusrc/praetor/agents-md)<a href="https://agentmods.dev/instructions/tyrusrc/praetor/agents-md"><img src="https://agentmods.dev/badge/instructions/tyrusrc/praetor/agents-md.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 | $0.03495 | $0.03495 |
| Opus 5 | $0.01747 | $0.01747 |
| Sonnet 5 | $0.00699 | $0.00699 |
| Haiku 4.5 | $0.00349 | $0.00349 |
Grade A, and why
praetor AGENTS.md 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 5d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Team Configuration
This project uses specialized agents for parallel pentesting. The orchestrator (main conversation) dispatches agents for independent work streams, merges results, and makes strategic decisions.
Definition Files
Each role below corresponds to a file in .claude/agents/<role>.md that the Agent tool auto-loads when dispatched by name. Update both this file (role overview) AND the agent file (operational detail) when changing a role.
The orchestrator role is split out: grow-agent is the session-lifecycle orchestrator, defined in .claude/agents/grow-agent.md. When invoked, grow-agent dispatches the 9 roles below.
Command Tier (above grow-agent)
Two engagement leads sit above grow-agent. They own strategy — research, a written plan, multi-domain dispatch, cross-target synthesis, delivery — and do NOT run the per-domain loop themselves. Both invoke the shared SOP .claude/skills/command-engagement.md; each agent file carries only its role deltas. On-demand only.
{pentest|redteam}-commander engagement lead — research, plan, synthesize, report
└─ grow-agent(domain) × N per-domain executor (bounded: 2–3 in flight)
└─ 10 workers
pentest-commander
Purpose: Coverage-driven engagement lead. Full WSTG/OWASP coverage, every finding verified and reported.
When to dispatch: Multi-endpoint / multi-domain pentest where breadth + a findings report is the deliverable.
Dispatch: Agent(subagent_type="pentest-commander", prompt="domains=[...], objective=..., session_name=...").
Success: coverage matrix complete (or documented negatives), all findings confirmed + written up, report in reports/.
redteam-commander
Purpose: Objective-driven engagement lead. Shortest verified kill chain to a stated goal, under a stealth/noise budget.
When to dispatch: Goal-oriented red team op (reach data/access/flag) rather than a coverage sweep.
Dispatch: Agent(subagent_type="redteam-commander", prompt="objective=..., domains=[...], noise_budget=low|moderate|high").
Success: objective reached + kill chain documented, or furthest-progress chain + blocker.
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.
- 5d ago First seen · 207 lines · 3,495 tokens per session scan A d9ee657fd90f
praetor AGENTS.md is an instructions file published in the GitHub repository TyrusRC/praetor (5 stars, last pushed today), licensed Apache-2.0. It adds 3,495 tokens to every session, about $0.0175 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 instructions, from other repositories
communitytools CLAUDE.md
Claude Code instructions for transilienceai/communitytools, covering community security tools repository, role, standing principles, skill selection and agent architecture.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
hometax-doum AGENTS.md
AGENTS.md instructions for lbiz-partners/hometax-doum, covering claude.md — hometax-doum 개발 규칙 (하네스와 쌍), 규칙 ↔ 강제 장치 and 운용 메모.
powerglide AGENTS.md
Instructions for bkataru/powerglide, covering powerglide agent protocol & integration guide, the ralph loop protocol, termination signals, velocity control and reliable pty execution.
agent-plugins-skills AGENTS.md
AGENTS.md instructions for richfrem/agent-plugins-skills, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.