bugs

bugs is a skill for Claude Code, Codex from Kevin-Liu-01/Agent-Machines. It costs 56 tokens per session (1,909 once invoked), scanned A, original, MIT.

A security and correctness audit that searches important code for real bugs, such as access-control bypasses, unsafe input handling, memory errors, and resource leaks. CTF means a challenge-style security exercise.

In plain words
What is it for?
Use it before shipping a security-sensitive subsystem, after a vulnerability is reported, or to inspect a selected part of a codebase.
Why use it?
It helps find serious defects that ordinary style reviews or general testing may miss, while avoiding reports based only on minor issues.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it before shipping a security-sensitive subsystem, after a vulnerability is reported, or to inspect a selected part of a codebase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevin-liu-01/agent-machines/bugs
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 Kevin-Liu-01/Agent-Machines --skill bugs
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

Made for: Claude Code, Codex.

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 bugs

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/bugs/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/bugs)
Your own site
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/bugs"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/bugs/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 bugs

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/bugs"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/bugs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,909 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00056 $0.01909
Opus 5 $0.00028 $0.00955
Sonnet 5 $0.00011 $0.00382
Haiku 4.5 $0.00006 $0.00191

Measured 10d ago against content hash f7593fea9cfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bugs 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.

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.

knowledge/skills/bugs/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bugs

Adversarial bug hunt. Dispatch one subagent per critical file with the mandate: "There exists a security or correctness bug in this file. Locate it or admit that you are unable to."

When to use

  • Before shipping a new subsystem to production
  • After a CVE drops in a dependency or peer project
  • When reviewing code that handles untrusted input
  • Periodic security hygiene on the attack surface
  • When the user says /bugs or /bugs <scope>

Philosophy

This is a CTF, not a code review. We are not looking for style nits, pedantic warnings, or non-malignant nits. We want:

  • Memory safety violations (OOB, use-after-free, UB)
  • Logic bugs (inverted checks, missing validation, TOCTOU)
  • Resource leaks that lead to DoS (FD exhaustion, OOM, orphaned processes)
  • Auth/authz bypasses
  • Input validation gaps (path traversal, integer truncation, injection)
  • Protocol violations (wrong constants, spec non-compliance)
  • State machine violations (DFA lies, skipped cleanup)

It is OK for an agent to admit failure. A false negative is better than a false positive. We do not reward noise.

Scope

  • /bugs -- audit the full attack surface (DHV + DCS runtime)
  • /bugs dhv -- audit only packages/rust/dhv/
  • /bugs dcs -- audit only apps/cloud/apps/dcs/src/runtime/
  • /bugs <path> -- audit specific files or directories

Procedure

Phase 1: Map the attack surface

Dispatch an Explore agent to identify security-critical files. Criteria for "critical":

  • Processes untrusted input (guest MMIO, network, gRPC, file I/O)
  • Contains unsafe code or FFI
  • Handles authentication, authorization, or secrets
  • Manages system resources (cgroups, TAP devices, fds, mmap)
  • Implements cryptographic or protocol logic
  • Snapshot/restore/migration paths (deserialize from untrusted source)

The explorer returns absolute paths ranked by attack surface. Target 20-30 files for a full audit.

Phase 2: Dispatch hunters

Launch one background Agent per file (or small file group). Each agent gets this exact prompt template:

Read the full file on GitHub · 207 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.

  1. 10d ago First seen · 207 lines · 56 tokens per session scan A f7593fea9cfd

Subscribe to this mod's changes

bugs is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (27 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,909 once invoked, about $0.0003 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.

Related

Other skills, from other repositories