What is PiRanha CLAUDE.md?

Project instructions for PiRanha, a Claude Code skill for automated bug-bounty hunting. Bug-bounty hunting means testing software for security weaknesses with the owner’s permission.

Use it when developing or operating PiRanha, including launching hunts, checking status, planning agent work, managing tools, and diagnosing installations.

It explains the project’s files, command-line launcher, specialist agents, and operating flow so developers can understand and maintain the system.

PiRanha CLAUDE.md — Instructions file for coding agents by Falcon-Forge: Project instructions for PiRanha, a Claude Code skill for…

Install

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.

agentmods

npx agentmods add instructions/falcon-forge/piranha/claude-md

Clone the repo

git clone --depth 1 https://github.com/Falcon-Forge/PiRanha

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/falcon-forge/piranha/claude-md.svg)](https://agentmods.dev/instructions/falcon-forge/piranha/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/falcon-forge/piranha/claude-md"><img src="https://agentmods.dev/badge/instructions/falcon-forge/piranha/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 568 This file is loaded in full into every session.

When invoked 568 The same file — it is already loaded in full.

Security scan C 2 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00568	$0.00568
Opus 5	$0.00284	$0.00284
Sonnet 5	$0.00114	$0.00114
Haiku 4.5	$0.00057	$0.00057

Measured 5d ago against content hash c47edb161153, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

PiRanha CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- Binary: `bun run build` (this host) or `bun run build:all` (cross-platform → `dist/piranha-<platform>-<arch>`, attached to GitHub releases by `.github/workflows/release.yml`). Install via `curl -fsSL .../install.sh | s

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Binary: `bun run build` (this host) or `bun run build:all` (cross-platform → `dist/piranha-<platform>-<arch>`, attached to GitHub releases by `.github/workflows/release.yml`). Install via `curl -fsSL .../install.sh | s

CLAUDE.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BugHunter AI — Claude Code Configuration

This project is a Claude Code skill for autonomous bug bounty hunting.

Key Files

skills/BugBountyFramework/SKILL.md — Main skill definition (loaded by Claude Code)
cli/piranha.ts — the piranha launcher binary (compiled via bun build --compile). Classifies a target, drives the hunt-orchestrator state machine, computes the router plan, and launches the harness (omp/pi or Claude Code). Standalone subcommands: hunt, status, plan, agents, engagements, tools (per-domain dynamic tooling/MCP capture + PATH check), vault, install, doctor, completions, update.
skills/BugBountyFramework/Agents/*.md — 53 specialized agents (51 hunters/specialists + ValidatorAgent + ExploitChainAgent)
skills/BugBountyFramework/Tools/*.ts — TypeScript tools (Bun runtime)
skills/BugBountyFramework/Tools/agent-router.ts — engagement type → ordered, dependency-aware agent deployment plan
package.json — Pi package manifest (pi.skills); this repo is the PiRanha Pi package and installs the skill as piranha via pi install git:github.com/h4ckologic/PiRanha

How It Works

When a user types hunt <target>, Claude Code loads SKILL.md which orchestrates a 10-phase hunt:

State machine initialization (hunt-orchestrator.ts)
Credential loading from vault (credential-vault.ts)
Authentication flow (auth-manager.ts)
Application profiling via Playwright
Reconnaissance
Parallel agent deployment (each agent is a .md file)
Dynamic testing via Burp + Playwright
Vulnerability assessment
Learning & pattern update
Report generation

Development

Tools are TypeScript/Bun. Run with bun <tool>.ts --help
Binary: bun run build (this host) or bun run build:all (cross-platform → dist/piranha-<platform>-<arch>, attached to GitHub releases by .github/workflows/release.yml). Install via curl -fsSL .../install.sh | sh.
The three core tools double as importable libraries (guarded by import.meta.main) and standalone CLIs — cli/piranha.ts bundles them; bun <tool>.ts still runs each directly.
Agents are Markdown files with structured instructions
Test against your own targets or sanctioned bug bounty programs only

Read the full file on GitHub · 32 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.

5d ago First seen · 32 lines · 568 tokens per session scan C c47edb161153

Subscribe to this mod's changes

PiRanha CLAUDE.md is an instructions file published in the GitHub repository Falcon-Forge/PiRanha (5 stars, last pushed 2mo ago), licensed MIT. It adds 568 tokens to every session, about $0.0028 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security

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.

openai/codex · 5,182 tokens

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 · 6,785 tokens

PiRanha CLAUDE.md