Agent skill

Bug Hunt

Run adversarial bug hunting on your codebase. An agent skill from danpeg/bug-hunt.

MITAuto-check passed

Install Bug Hunt

skills CLI

$ npx skills add danpeg/bug-hunt --skill bug-hunt -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install danpeg/bug-hunt bug-hunt --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "bug-hunt" agent skill from https://github.com/danpeg/bug-hunt/tree/main into .claude/skills/bug-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-hunt", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add danpeg/bug-hunt --skill bug-hunt -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install danpeg/bug-hunt bug-hunt --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "bug-hunt" agent skill from https://github.com/danpeg/bug-hunt/tree/main into .agents/skills/bug-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-hunt", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add danpeg/bug-hunt --skill bug-hunt -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install danpeg/bug-hunt bug-hunt --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "bug-hunt" agent skill from https://github.com/danpeg/bug-hunt/tree/main into .cursor/skills/bug-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-hunt", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add danpeg/bug-hunt --skill bug-hunt -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install danpeg/bug-hunt bug-hunt --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "bug-hunt" agent skill from https://github.com/danpeg/bug-hunt/tree/main into .gemini/skills/bug-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-hunt", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install danpeg/bug-hunt bug-hunt

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add danpeg/bug-hunt --skill bug-hunt -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "bug-hunt" agent skill from https://github.com/danpeg/bug-hunt/tree/main into .github/skills/bug-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-hunt", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add danpeg/bug-hunt --skill bug-hunt -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install danpeg/bug-hunt bug-hunt --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "bug-hunt" agent skill from https://github.com/danpeg/bug-hunt/tree/main into .opencode/skills/bug-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-hunt", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: bug-hunt
GitHub stars: 146
Token cost: ~968 tokens
SKILL.md length: 504 words
Files: 13
Skills in repo: 1
Repo updated: Mar 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Run adversarial bug hunting on your codebase. An agent skill from danpeg/bug-hunt.

Works in 6 steps: Parse arguments and resolve target → Read the prompt files → Run the Hunter Agent → …
SKILL.md covers Usage, Target and Execution Steps
Calls git

What it does

Bug Hunt is an agent skill from danpeg/bug-hunt. Run adversarial bug hunting on your codebase. Uses 3 isolated agents (Hunter, Skeptic, Referee) to find and verify real bugs with high fidelity. Invoke with /bug-hunt, /bug-hunt [path], or /bug-hunt -b <branch [--base <base].

Its SKILL.md is about 970 tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files (for example `.github/ISSUE_TEMPLATE/bug_report.md`, `.github/ISSUE_TEMPLATE/feature_request.md` and `.github/PULL_REQUEST_TEMPLATE.md`).

The repository describes itself as: Adversarial bug hunting skill for Claude Code. 3 isolated agents (Hunter, Skeptic, Referee) find and verify real bugs. The licence is MIT.

Example prompts

“/bug-hunt”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

Parse arguments and resolve target
Read the prompt files
Run the Hunter Agent
Run the Skeptic Agent
Run the Referee Agent
Present the Final Report

What it can do on your machine

Read from SKILL.md and the folder at commit 5614e19. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bug Hunt loads about 968 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 504 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~59
When it runs · the whole SKILL.md, loaded when a task matches: ~968

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from danpeg/bug-hunt at commit 5614e19, republished under its MIT licence (© danpeg). 504 words, ~968 tokens.

Download SKILL.mdSave it as .claude/skills/bug-hunt/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.

name: bug-hunt
description: Run adversarial bug hunting on your codebase. Uses 3 isolated agents (Hunter, Skeptic, Referee) to find and verify real bugs with high fidelity. Invoke with /bug-hunt, /bug-hunt [path], or /bug-hunt -b <branch> [--base <base>].
argument-hint: [path | -b <branch> [--base <base-branch>]]
disable-model-invocation: true

Bug Hunt - Adversarial Bug Finding

Run a 3-agent adversarial bug hunt on your codebase. Each agent runs in isolation.

Usage

/bug-hunt              # Scan entire project
/bug-hunt src/         # Scan specific directory
/bug-hunt lib/auth.ts  # Scan specific file
/bug-hunt -b feature-xyz              # Scan files changed in feature-xyz vs main
/bug-hunt -b feature-xyz --base dev   # Scan files changed in feature-xyz vs dev

Target

The raw arguments are: $ARGUMENTS

Parse the arguments as follows:

If arguments contain -b <branch>: this is a branch diff mode.
- Extract the branch name after -b.
- If --base <base-branch> is also present, use that as the base branch. Otherwise default to main.
- Run git diff --name-only <base>...<branch> using the Bash tool to get the list of changed files.
- If the command fails (e.g. branch not found), report the error to the user and stop.
- If no files changed, tell the user there are no changes to scan and stop.
- The scan target is the list of changed files (scan their full contents, not just the diff).
If arguments do NOT contain -b: treat the entire argument string as a path target (file or directory). If empty, scan the current working directory.

Execution Steps

You MUST follow these steps in exact order. Each agent runs as a separate subagent via the Agent tool to ensure context isolation.

Step 1: Parse arguments and resolve target

Follow the rules in the Target section above to determine the scan target. If in branch diff mode, run the git diff command now and collect the file list.

Step 2: Read the prompt files

Read these files using the skill directory variable:

${CLAUDE_SKILL_DIR}/prompts/hunter.md
${CLAUDE_SKILL_DIR}/prompts/skeptic.md
${CLAUDE_SKILL_DIR}/prompts/referee.md

Step 3: Run the Hunter Agent

Launch a general-purpose subagent with the hunter prompt. Include the scan target in the agent's task. If in branch diff mode, pass the explicit file list so the Hunter only scans those files (full contents). The Hunter must use tools (Read, Glob, Grep) to examine the actual code.

Wait for the Hunter to complete and capture its full output.

Show full SKILL.md (206 more words)Show less

Step 3b: Check for findings

If the Hunter reported TOTAL FINDINGS: 0, skip Steps 4-5 and go directly to Step 6 with a clean report. No need to run Skeptic and Referee on zero findings.

Step 4: Run the Skeptic Agent

Launch a NEW general-purpose subagent with the skeptic prompt. Inject the Hunter's structured bug list (BUG-IDs, files, lines, claims, evidence, severity, points). Do NOT include any narrative or methodology text outside the structured findings.

The Skeptic must independently read the code to verify each claim.

Wait for the Skeptic to complete and capture its full output.

Step 5: Run the Referee Agent

Launch a NEW general-purpose subagent with the referee prompt. Inject BOTH:

The Hunter's full bug report
The Skeptic's full challenge report

The Referee must independently read the code to make final judgments.

Wait for the Referee to complete and capture its full output.

Step 6: Present the Final Report

Display the Referee's final verified bug report to the user. Include:

The summary stats
The confirmed bugs table (sorted by severity)
Low-confidence items flagged for manual review
A collapsed section with dismissed bugs (for transparency)

If zero bugs were confirmed, say so clearly — a clean report is a good result.

Files

SKILL.md and 12 other files in the repository root of danpeg/bug-hunt.

SKILL.md
.github/ISSUE_TEMPLATE/bug_report.md
.github/ISSUE_TEMPLATE/feature_request.md
.github/PULL_REQUEST_TEMPLATE.md
.gitignore
CHANGELOG.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
README.md
prompts/hunter.md
prompts/referee.md
prompts/skeptic.md

Open the folder on GitHubat commit 5614e19

Compare with similar skills

Bug Hunt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bug Hunt compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Bug Hunt this skilldanpeg/bug-hunt	146	—	~968	Automated safety check: Pass	MIT	7 mo ago
Hunt Graphqlsickn33/agentic-awesome-skills	47k	1 repos	~5.7k	Automated safety check: Pass	MIT	2 days ago
Hunt Dispatchsickn33/agentic-awesome-skills	47k	1 repos	~5k	Automated safety check: Notes	MIT	2 days ago
Hunt Sharepointsickn33/agentic-awesome-skills	47k	1 repos	~8.5k	Automated safety check: Pass	MIT	2 days ago
Hunt Subdomainsickn33/agentic-awesome-skills	47k	1 repos	~6.7k	Automated safety check: Pass	MIT	2 days ago
Hunt Lfisickn33/agentic-awesome-skills	47k	1 repos	~4.7k	Automated safety check: Warn	MIT	2 days ago

Similar skills

Hunt Graphql
sickn33/agentic-awesome-skills
Hunting skill for graphql vulnerabilities. An agent skill from sickn33/agentic-awesome-skills.
47k GitHub starsUsed in 1 repo~5.7k tokens
Backend & APIsAuto-check passed
Hunt Dispatch
sickn33/agentic-awesome-skills
Skill-set loader for /hunt orchestrator. An agent skill from sickn33/agentic-awesome-skills.
47k GitHub starsUsed in 1 repo~5k tokens
Auto-check: notes
Hunt Sharepoint
sickn33/agentic-awesome-skills
Hunt Microsoft SharePoint Server (2013/2016/2019/Subscription Edition) on-prem farms
47k GitHub starsUsed in 1 repo~8.5k tokens
Documents & OfficeAuto-check passed
Hunt Subdomain
sickn33/agentic-awesome-skills
Hunting skill for subdomain takeover vulnerabilities. An agent skill from sickn33/agentic-awesome-skills.
47k GitHub starsUsed in 1 repo~6.7k tokens
Auto-check passed
Hunt Lfi
sickn33/agentic-awesome-skills
Hunt Local File Inclusion (LFI), Remote File Inclusion (RFI), and Path Traversal
47k GitHub starsUsed in 1 repo~4.7k tokens
Auto-check: warnings
Threat Hunting
sickn33/agentic-awesome-skills
Blue-team threat hunting: detection engineering with Sigma/YARA, SIEM query design, and validation of incident detections against known technique patterns.
47k GitHub starsUsed in 1 repo~474 tokens
SecurityAuto-check passed

Questions about Bug Hunt

What does Bug Hunt do?

Run adversarial bug hunting on your codebase. An agent skill from danpeg/bug-hunt. Bug Hunt is an agent skill from danpeg/bug-hunt. Run adversarial bug hunting on your codebase.

How do I install Bug Hunt in Claude Code?

Run `npx skills add danpeg/bug-hunt --skill bug-hunt -a claude-code`. Or copy the skill folder (the danpeg/bug-hunt repository) into .claude/skills/bug-hunt in your project. Claude Code loads it when a task matches its description.

How do I install Bug Hunt in Codex?

Run `npx skills add danpeg/bug-hunt --skill bug-hunt -a codex`. Or copy the skill folder (the danpeg/bug-hunt repository) into .agents/skills/bug-hunt in your project. Codex loads it when a task matches its description.

Can I use Bug Hunt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add danpeg/bug-hunt --skill bug-hunt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bug-hunt, .gemini/skills/bug-hunt, .github/skills/bug-hunt and .opencode/skills/bug-hunt in your project.

What does Bug Hunt need to run?

Going by SKILL.md and its folder, Bug Hunt needs the command-line tools its instructions call (git).

Does Bug Hunt access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Bug Hunt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Bug Hunt use?

Bug Hunt is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bug Hunt use?

About 968 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bug Hunt?

Skills that share tags, products or a category with Bug Hunt: Hunt Graphql (sickn33/agentic-awesome-skills, 47k stars), Hunt Dispatch (sickn33/agentic-awesome-skills, 47k stars), Hunt Sharepoint (sickn33/agentic-awesome-skills, 47k stars) and Hunt Subdomain (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bug Hunt?

danpeg (a GitHub user) maintains it in danpeg/bug-hunt, which has 146 GitHub stars. The repository was last updated on March 5, 2026.

Source: danpeg/bug-hunt on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Bug Hunt

Facts

At a glance

What it does

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Bug Hunt - Adversarial Bug Finding

Usage

Target

Execution Steps

Step 1: Parse arguments and resolve target

Step 2: Read the prompt files

Step 3: Run the Hunter Agent

Step 3b: Check for findings

Step 4: Run the Skeptic Agent

Step 5: Run the Referee Agent

Step 6: Present the Final Report

Files

Compare with similar skills

Similar skills

Hunt Graphql

Hunt Dispatch

Hunt Sharepoint

Hunt Subdomain

Hunt Lfi

Threat Hunting

Questions about Bug Hunt