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/awarexone/agentic-bug-hunter/agents-mdgit clone --depth 1 https://github.com/Awarexone/Agentic-Bug-HunterWhat 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 | $0.02384 | $0.02384 |
| Opus 5 | $0.01192 | $0.01192 |
| Sonnet 5 | $0.00477 | $0.00477 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
Agentic-Bug-Hunter 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 2d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Bounty Agent Toolkit — Plugin Guide
This repo is an agent-portable bug bounty plugin for professional hunting across HackerOne, Bugcrowd, Intigriti, and Immunefi. It supports Claude Code, OpenCode, Pi Agent, Codex-style Agent Skills, and shared .agents/skills harnesses.
What's Here
Skills (13 domains — load with /bug-bounty, /web2-recon, /token-scan, etc.)
| Skill | Domain |
|---|---|
skills/bug-bounty/ |
Master workflow — recon to report, all vuln classes, LLM testing, chains |
skills/bb-methodology/ |
Hunting mindset + 5-phase non-linear workflow + tool routing + session discipline |
skills/web2-recon/ |
Subdomain enum, live host discovery, URL crawling, nuclei |
skills/web2-vuln-classes/ |
21 bug classes with bypass tables (SSRF, open redirect, file upload, Agentic AI) |
skills/security-arsenal/ |
Payloads, bypass tables, gf patterns, always-rejected list |
skills/web3-audit/ |
10 smart contract bug classes, Foundry PoC template, pre-dive kill signals |
skills/meme-coin-audit/ |
Meme coin rug pull detection, token authority checks, bonding curve exploits, LP attacks |
skills/report-writing/ |
H1/Bugcrowd/Intigriti/Immunefi report templates, CVSS 3.1, human tone |
skills/triage-validation/ |
7-Question Gate, 4 gates, never-submit list, conditionally valid table |
skills/credential-attack/ |
Password spray methodology — when/why, 4-stage pipeline, mode selection, lockout tactics, legal guardrails |
skills/mobile-pentest/ |
Android/iOS app pentest — runtime-first proxy workflow, APK/IPA decompile, deeplink injection, WebView bridge |
skills/cicd-security/ |
CI/CD pipeline hunting — GitHub Actions injection, secret exfil, self-hosted runner poisoning |
skills/graphql-audit/ |
GraphQL hunting — introspection, field suggestions, batching DoS, IDOR via aliasing, injection |
Commands (slash commands)
Note: All commands are prefixed to avoid conflicts with Codex's built-in commands.
/resumeis a reserved Codex command — use/pickupto continue a previous hunt.
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.
- 2d ago First seen · 147 lines · 2,384 tokens per session scan A 01810cab9838
Agentic-Bug-Hunter AGENTS.md is an instructions file published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,651 stars, last pushed yesterday), licensed MIT. It adds 2,384 tokens to every session, about $0.0119 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 2026-08-30.
Other instructions, from other repositories
open-kritt AGENTS.md
AGENTS.md instructions for Kritt-ai/open-kritt, covering agents.md, what this is, run / build / test, frontend and backend (needs databaseurl; see .env.example).
claudit-sec CLAUDE.md
Instructions for HarmonicSecurity/claudit-sec, covering claudit-sec — claude security audit tool, project overview, architecture, data collectors and key paths.
Threatswarm CLAUDE.md
Instructions for mukul975/Threatswarm, covering cybersecurity workspace — master context, scope enforcement (mandatory — zero exceptions), tool paths, agent delegation table and opsec defaults.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.