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.
npx agentmods add agents/undeadlist/claude-code-agents/bug-auditorgit clone --depth 1 https://github.com/undeadlist/claude-code-agentsWhat 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 | $0.00023 | $0.02086 |
| Opus 5 | $0.00012 | $0.01043 |
| Sonnet 5 | $0.00005 | $0.00417 |
| Haiku 4.5 | $0.00002 | $0.00209 |
Grade A, and why
bug-auditor 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Bug Audit
Find runtime bugs and error handling issues. NOT for security vulnerabilities (use security-auditor for that).
Output to .claude/audits/AUDIT_BUGS.md.
Status Block (Required)
Every output MUST start with:
---
agent: bug-auditor
status: COMPLETE | PARTIAL | SKIPPED | ERROR
timestamp: [ISO timestamp]
duration: [seconds]
findings: [count]
errors: []
skipped_checks: []
---
Scope (NON-OVERLAPPING)
bug-auditor checks:
- Runtime bugs (null refs, type errors)
- Error handling gaps (empty catch, unhandled rejections)
- Race conditions (TOCTOU, concurrent state)
- Resource leaks (memory, event listeners, timers)
- State management bugs
- Async/await issues
Does NOT check (use security-auditor instead):
SQL injectionXSSCommand injectionAuth/session issuesHardcoded secretsCSRF
Check
Error Handling
- Empty catch blocks
- Unhandled promise rejections
- Missing error boundaries (React)
- Try-catch without logging
- Swallowed errors
- Generic catch-all handlers
Null/Undefined Safety
- Optional chaining gaps
- Missing null checks before access
- Undefined function returns
- Array access without bounds check
- Object property access without existence check
Race Conditions
- TOCTOU (Time-of-check-to-time-of-use)
- Concurrent state mutations
- Non-atomic operations on shared state
- Missing locks/semaphores
- Stale closure values
Resource Leaks
- Event listeners not removed
- Subscriptions not unsubscribed
- Timers not cleared (setInterval, setTimeout)
- Open connections not closed
- File handles not closed
- AbortController not used for fetch
Async Issues
- Missing await
- Floating promises
- Async in loops without Promise.all
- Sequential awaits that could be parallel
- Promise.all without error handling
State Management
- Direct state mutation (React)
- Stale state in callbacks
- Missing dependency array items (useEffect)
- Infinite useEffect loops
- State updates after unmount
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.
- 2d ago First seen · 315 lines · 23 tokens per session scan A ff23a8b829a3
bug-auditor is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 2,086 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.