agentmods.dev

bughunt-cursor

bughunt-cursor is a command for Claude Code from robzilla1738/roberts-skills. It costs 38 tokens per session (835 once invoked), scanned A, original, MIT.

A report-only code bug hunt that uses the Cursor command-line tool to examine selected files, modules, changes, or an entire repository. It sends parts of the search to several code-analysis models and includes a separate skeptical review of findings.

In plain words
What is it for?
Use it to inspect a diff, staged changes, a path, a module, or a whole repository for possible bugs.
Why use it?
It reduces the manual effort of searching a codebase for bugs while helping challenge findings that may be false positives.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the bughunt-suite plugin — 3 skills, 4 commands shipped together

not rated 5repo 3mo ago A scan 38 tokens original MIT

Good fit Use it to inspect a diff, staged changes, a path, a module, or a whole repository for possible bugs.

Compare 6 commands from other repositories ↓
View source ↗ robzilla1738/roberts-skills robertcourson.com
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add robzilla1738/roberts-skills
Claude Code
/plugin install bughunt-suite

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.

agentmods badge for bughunt-cursor

README.md
[![agentmods](https://agentmods.dev/badge/commands/robzilla1738/roberts-skills/bughunt-cursor/github.svg)](https://agentmods.dev/commands/robzilla1738/roberts-skills/bughunt-cursor)
Your own site
<a href="https://agentmods.dev/commands/robzilla1738/roberts-skills/bughunt-cursor"><img src="https://agentmods.dev/badge/commands/robzilla1738/roberts-skills/bughunt-cursor/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.

agentmods 80×15 button for bughunt-cursor

Your own site · 80×15
<a href="https://agentmods.dev/commands/robzilla1738/roberts-skills/bughunt-cursor"><img src="https://agentmods.dev/badge/commands/robzilla1738/roberts-skills/bughunt-cursor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 835 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00835
Opus 5 $0.00019 $0.00417
Sonnet 5 $0.00008 $0.00167
Haiku 4.5 $0.00004 $0.00084

Measured 8d ago against content hash 5741243f288f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bughunt-cursor 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 8d 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.

plugins/bughunt-suite/commands/bughunt-cursor.md · 48 lines

What it actually says

Run a fast bug hunt against: $ARGUMENTS

Same hunt, faster substrate: the (lens × hotspot) grid is fanned out by the Cursor CLI (cursor-agent) on a fast model (Composer 2.5 / Grok) instead of the Workflow tool, while the mandatory skeptic pass stays on a strong reasoner (Opus 4.8). This is Rung A-CLI of the capability ladder — usable inside Cursor, Claude Code, or any shell with cursor-agent on PATH.

Load and follow the bughunt skill at ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/SKILL.md exactly, selecting the Rung A-CLI path in orchestration.md.

Parse $ARGUMENTS for scope (diff · staged · a path · a module · empty = whole repo), depth (quick · deep, default deep), and an optional hunt-model id (default composer-2.5; discover ids with cursor-agent --list-models).

Then run the loop:

  1. Preflight — confirm cursor-agent is on PATH (cursor-agent --version) and auth is set (CURSOR_API_KEY or a prior cursor-agent login). If it is not available, fall back to the standard /bughunt rungs (Workflow / Tasks / sequential) and say so.
  2. Recon & pre-pass — detect platform, map trust boundaries, and run the deterministic pre-pass: python3 ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/scripts/bughunt.py census, hotspots, signals, deps (see tooling.md). On a large/unfamiliar repo, confirm scope first.
  3. Build the grid — form cells: [{ lens, platform, area, files, lensPath, platformPath }] (absolute spoke paths under ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/) and write cells.json.
  4. Hunt + Verify (one command) — 
    node ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/scripts/hunt-cursor.mjs \
    --cells cells.json --workspace "$PWD" \
    --hunt-model composer-2.5 --verify-model claude-opus-4-8-thinking-high \
  | python3 ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/scripts/bughunt.py merge - \
      --require-verified --require-coverage --strict --write-baseline
    Hunters are read-only (--mode ask, never --force). Keep the verify model strong — do not move the skeptic pass to the fast model.
  5. Report — python3 ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/scripts/bughunt.py render .bughunt/findings.json emits ranked markdown (+ HTML + SARIF) into .bughunt/.

This is report-only: surface and prove bugs, do not edit code unless I ask. To then prove high-value Probable findings at runtime in parallel sandboxes, see the optional Confirm rung in confirm.md. If $ARGUMENTS is empty, ask what to hunt and which depth.

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.

  1. 8d ago First seen · 48 lines · 38 tokens per session scan A 5741243f288f

Subscribe to this mod's changes

bughunt-cursor is a command published in the GitHub repository robzilla1738/roberts-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 835 once invoked, about $0.0002 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.

Debuggingagent-skillsaiappkitcoding-assistantdesign-systemhuman-interface-guidelines
Related

Other commands, from other repositories

fix-issues

Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.

can1357/oh-my-pi · 0 tokens

maintainer-review-error-handling

Review the PR for error-handling correctness — surfaced errors, no silent swallows, consistent error patterns (Pi-tuned).

coleam00/Archon · 25 tokens

investigate

Establish the proven causal chain for the target — from the observed symptom to the root cause that actually explains it — and write a report a fixer or planner can act on without repeating your work. You change nothing and fix nothing: the repository must be exactly as you found it when you finish. No one watches the…

coleam00/Archon · 0 tokens

review-errors

Find one defect: a real failure crosses the changed code and becomes indistinguishable from success to the caller, operator, or user who must react. Not every error needs logging; recovery is correct when the contract permits it and the right owner can still observe the outcome. Read-only: never modify files, commit…

coleam00/Archon · 0 tokens

error-flow

Design an error flow end to end — prevention, detection, messaging, and recovery paths.

Owl-Listener/designer-skills · 18 tokens

ux-fix

Opt-in fix loop. Reads the latest report from .ux/, validates working tree, and applies findings as atomic commits via the right sub-agents. Triggers on "fix the findings", "apply the fixes", or "run the fix loop". Use when applying findings from a previous audit / copy / a11y / motion / polish report, the user says…

Laith0003/ux-skill · 129 tokens