agentmods.dev

praetor: Instructions file for Gemini CLI

GEMINI.md

praetor GEMINI.md is an instructions file for Gemini CLI from TyrusRC/praetor. It costs 1,083 tokens per session, scanned C, original, Apache-2.0.

A set of operating instructions for Praetor, an authorized security-testing and red-team tool. It explains how to find its tools and playbooks, check whether a target is in scope, and follow the project’s security rules.

In plain words
What is it for?
Use it when operating Praetor through the Gemini CLI or Antigravity. It covers choosing security-testing tools, loading procedural playbooks, checking scope, and using the required browser or network path.
Why use it?
It helps prevent security tests from being sent to unauthorized domains or through the wrong network route. It also directs the agent to the project’s authoritative tools, skills, and rules instead of guessing how to use them.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is TyrusRC/praetor's own configuration. It tells Gemini CLI how to work on praetor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything praetor configures →

not rated 7repo +1 changed 1mo ago C scan 1,083 tokens original Apache-2.0
View source ↗ TyrusRC/praetor
Reuse

Borrowing it

Nothing to install: this file belongs to TyrusRC/praetor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TyrusRC/praetor/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/TyrusRC/praetor

Made for: Gemini CLI.

Wrote 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.

agentmods badge for praetor GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tyrusrc/praetor/gemini-md/github.svg)](https://agentmods.dev/instructions/tyrusrc/praetor/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/tyrusrc/praetor/gemini-md"><img src="https://agentmods.dev/badge/instructions/tyrusrc/praetor/gemini-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for praetor GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tyrusrc/praetor/gemini-md"><img src="https://agentmods.dev/badge/instructions/tyrusrc/praetor/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,083 This file is loaded in full into every session.
When invoked 1,083 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01083 $0.01083
Opus 5.5 $0.00433 $0.00433
Sonnet 5.5 $0.00217 $0.00217
Haiku 4.5 $0.00108 $0.00108

Measured 1mo ago against content hash de6d4f9f2464, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

praetor GEMINI.md scanned grade C with 1 finding 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 1mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

2. **No destructive payloads.** No `DROP TABLE` / `DELETE FROM` / `rm -rf` /
GEMINI.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Praetor — operating guide for Gemini CLI & Antigravity

Praetor is an authorized pentest / red-team harness. Its capabilities are the Praetor MCP tools (register the server first — see README.md → Install into your agent, or examples/mcp-clients/). This file is the portable rule set; the full Claude-Code manual is CLAUDE.md, the agent roster is AGENTS.md.

Find capabilities and playbooks

  • Bootstrap (do this first): call praetor_bootstrap(). It returns the session-start flow (web / network / mobile lanes + the save-finding pipeline) and points to the rules, skills, and agent playbooks below.
  • Tools (what to run): call list_tier1_tools() or pick_tool(task). Web lane routes through Burp (127.0.0.1:8111); network lane bypasses Burp.
  • Rules (authoritative): call get_rules("hunting"), get_rules("engineering") and get_rules("project") — the always-active rules plus the project CLAUDE.md (save-finding gates, override surfaces, output discipline) as a tool (also burp://rules/* resources if your host supports them).
  • Skills (how to run it): call list_skills() then get_skill("<name>") — the procedural playbooks (verify-finding, chain-findings, lab-solve, craft-payload, …). Also on burp://skills/* for resource-capable hosts.
  • Prompts (one-call launchers): call list_prompts() then get_prompt("<name>", args) — hunt-target, triage-program, save-finding-checklist, … — the MCP prompt templates as tools, for hosts that defer the Prompts primitive.
  • Knowledge (probe classes): call list_knowledge() then get_knowledge("<cat>") — the KB matchers + craft guidance auto_probe consumes (also burp://knowledge/*).
  • Agents (strategy playbooks): call list_agents() then get_agent("<name>") (pentest-commander, recon-agent, auth-tester, …). If your host spawns sub-agents, give each one a get_agent playbook as its system prompt, and map the agent's tier (strategic / standard / fast) to your nearest model — not every host has Claude's opus/sonnet/haiku.

Read the full file on GitHub · 68 lines

Changes

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.

  1. 1mo ago Changed · +17 lines · +315 tokens per session de6d4f9f2464
  2. 1mo ago Changed · -5 tokens per session f3a2bb9662b6
  3. 1mo ago First seen · 51 lines · 773 tokens per session scan C 40b25ad95a9a

Subscribe to this mod's changes

praetor GEMINI.md is an instructions file published in the GitHub repository TyrusRC/praetor (7 stars, last pushed today), licensed Apache-2.0. It adds 1,083 tokens to every session, about $0.0043 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.

Building agentsClaude CodeSecurityburpsuiteclaude-skillspentestpentest-toolpentesting
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens