An adversarial workflow for searching the riskiest parts of a project for hidden bugs, usability problems, and inefficiencies. It produces a ranked report with supporting evidence and normally leaves product code unchanged.

It is for investigating projects such as apps, websites, services, and command-line tools, then documenting findings for a human or another review process to fix.

It focuses review effort on areas most likely to contain defects and filters findings through a required second check for false positives.

bughunt — Skill for Claude Code by robzilla1738

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.

Any agent

npx skills add robzilla1738/roberts-skills --skill bughunt

Clone the repo

git clone --depth 1 https://github.com/robzilla1738/roberts-skills

Made for: Claude Code.

Or install bughunt-suite, the plugin that ships this one along with the rest of its 3 skills, 4 commands.

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/skills/robzilla1738/roberts-skills/bughunt/github.svg)](https://agentmods.dev/skills/robzilla1738/roberts-skills/bughunt)

Your own site

<a href="https://agentmods.dev/skills/robzilla1738/roberts-skills/bughunt"><img src="https://agentmods.dev/badge/skills/robzilla1738/roberts-skills/bughunt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/robzilla1738/roberts-skills/bughunt"><img src="https://agentmods.dev/badge/skills/robzilla1738/roberts-skills/bughunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,013 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00156	$0.04013
Opus 5	$0.00078	$0.02006
Sonnet 5	$0.00031	$0.00803
Haiku 4.5	$0.00016	$0.00401

Measured 10d ago against content hash 22836760d7e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bughunt 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 10d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/bughunt.py, scripts/confirm-e2b.py, scripts/hunt-cursor.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/bughunt-suite/skills/bughunt/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bughunt

An offensive, hotspot-driven bug-hunting workflow. Where the autoreview skill (/review) is a defensive gate on your own diff, bughunt assumes the code is guilty and goes looking for hidden defects in the riskiest parts of the target with explicit coverage reporting.

Read this hub first, run recon, then open only the spokes your hunt plan selects.

Mission

Find the bugs that tests, linters, and a tired reviewer miss — and make each claim carry evidence. The output is a ranked, evidence-backed report, not a vibe. Default behavior is report-only: hunt, document, hand fixing to a human or the autoreview skill (/review). Never edit product code unless the user asks.

What makes this powerful (not just a checklist)

A deterministic spine — a bundled zero-dependency toolkit (bughunt.py) ranks hotspots by churn × complexity × boundary × test-gap, surfaces pain signals (aged TODOs, config drift, risky deps), and owns structured findings: fingerprint, dedupe, suppress, baseline-diff, and render to markdown/HTML/SARIF with CI exit codes. See tooling.md. Degrades to a pure-markdown pipeline when python3 is absent.
Breadth via fan-out — split the target into a grid of (lens × hotspot) cells and run them as independent parallel hunters, so every risky area is examined through every relevant lens. A capability ladder runs the same phases on whatever fan-out machinery the tool has — the Workflow tool, an external coding-CLI fan-out (Composer 2.5 / Grok via cursor-agent, the fast variant), parallel Tasks, or a sequential walk. See orchestration.md.
Depth via specialized lenses + platform catalogs — 13 lenses, each a distinct adversarial discipline (bugs, perf, DX, UX, supply-chain, data safety); each platform catalog encodes that ecosystem's specific footguns.
Signal via mandatory verify + triage — a skeptic pass tries to refute every finding before it's reported (verification.md); survivors are confidence-rated, cross-validated, and reproduced by triage.

Read the full file on GitHub · 229 lines

Files

What ships with it

30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 229 lines · 156 tokens per session scan A 22836760d7e2

Subscribe to this mod's changes

bughunt is a skill published in the GitHub repository robzilla1738/roberts-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 156 tokens to every session and 4,013 once invoked, about $0.0008 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.

Debugging agent-skills ai appkit coding-assistant design-system human-interface-guidelines

material-ui-nextjs

Integrates Material UI with Next.js App and Pages routers using @mui/material-nextjs, Emotion cache providers, next/font, CSS layers with Tailwind/CSS Modules, Link component prop patterns, CSS theme variables SSR notes, and App Router useSearchParams + Suspense. Use when setting up or debugging MUI in a Next.js app.

mui/material-ui · 76 tokens

find-bugs

Investigate reported or suspected bugs in this daisyUI monorepo, including proactive bug searches in packages/daisyui and packages/docs. Use when Codex must reproduce a defect, prove product impact, identify its root cause and isolation boundary, evaluate non-code solution options, or prepare a decision-ready bug-fix…

saadeghi/daisyui · 101 tokens

bughunt