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/kappa9999/white-hat-agent/agents-mdgit clone --depth 1 https://github.com/kappa9999/white-hat-agentWrote 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/kappa9999/white-hat-agent/agents-md)<a href="https://agentmods.dev/instructions/kappa9999/white-hat-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/kappa9999/white-hat-agent/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 | $0.00298 | $0.00298 |
| Opus 5 | $0.00149 | $0.00149 |
| Sonnet 5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
white-hat-agent 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 3d 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
White Hat Agent Core
- Build a model-neutral public application layer for composable, evidence-backed cyber discovery.
- Optimize for novel, causally verified, reproducible discoveries per unit of cost.
- Preserve exact target identity, evidence provenance, negative results, and alternate findings.
- Keep the corpus capable of representing techniques from every cyber domain and perspective. Execution scope is campaign data, not a knowledge-censorship mechanism.
- Keep the core target-neutral and model-neutral. Side effects belong behind explicit adapters; planners emit typed operations rather than tool-specific shell prose.
- Community knowledge must retain original language and source provenance, compile into strict versioned playbooks, and remain reviewable before promotion.
- MCP surfaces are namespaced, bounded, and structured. Prefer stdio and stateless Streamable HTTP; do not add SSE.
- Fleet mutations require explicit campaign, target, lease, and evidence identities.
- Every planning decision must be deterministic from the episode manifest and explain its score and blockers.
- A changed hypothesis revision may justify a new probe; an unchanged failed probe must not be retried blindly.
- Treat apparent success as a hypothesis until causal and differential checks establish the actual path.
- Use bounded replay or synthetic fixtures for routine tests. Adapter-specific integration tests own their environments.
- Use
apply_patchfor hand-authored changes and run corpus/schema validation,pytest,ruff check, package build, and MCP smoke tests before handoff.
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.
- 3d ago First seen · 20 lines · 298 tokens per session scan A 0215bf68bd1d
white-hat-agent AGENTS.md is an instructions file published in the GitHub repository kappa9999/white-hat-agent (0 stars, last pushed 15d ago), licensed Apache-2.0. It adds 298 tokens to every session, about $0.0015 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
stride-gpt AGENTS.md
Instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.
Cybermes AGENTS.md
Instructions for Zyrexnn/Cybermes, covering 🛡️ cybermes master operational directives (agents.md), 1. 🎯 persona & core mission, 2. ⚡ core operational principles, 3. 📁 strict target-scoped workspace & deliverables and mandatory rules for file creation.
cyber-neo CLAUDE.md
Instructions for Hainrixz/cyber-neo, covering cyber neo — contributor guidelines, what is cyber neo?, project structure, key design principles and contributing reference files.
numasec AGENTS.md
AGENTS.md instructions for FrancescoStabile/numasec, covering numasec agent guide, operating rules, branches, product direction and product messaging direction.
opencode-pentester CLAUDE.md
Claude Code instructions for humaidhahm/opencode-pentester, covering opencode-pentester, architecture, key files, subagents and permissions.
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).