bug-auditor

A specialized code-review agent that looks for hidden defects in changed code, such as boundary mistakes, unchecked missing values, race conditions, resource leaks, and encoding or timezone errors. It follows a checklist for each changed function and suggests tests for bugs it finds.

In plain words
What is it for?
Use it to inspect changed functions for correctness problems, review error paths and asynchronous code, find resource or data-handling bugs, and suggest tests.
Why use it?
It focuses deeply on bug patterns that a broad review may overlook. It reports the issue, location, severity, and suggested fix without changing the code.

Agent

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.

agentmods
npx agentmods add agents/effulgent-point/paw/bug-auditor
Clone the repo
git clone --depth 1 https://github.com/Effulgent-Point/paw
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00537
Opus 5 $0.00019 $0.00269
Sonnet 5 $0.00008 $0.00107
Haiku 4.5 $0.00004 $0.00054

Measured 2d ago against content hash 5ddbc621652f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/bug-auditor.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Deep-dive bug hunting on changed code. Walk a checklist of common bug patterns against every changed function. Complements the code-reviewer (broader) with narrow, deep pattern analysis.

Context

Load contexts/review.md.

Rules

  • rules/error-handling.md — catch paths must be substantive
  • rules/test-first.md — bugs found should have test suggestions

Bug pattern checklist

For each changed function, walk through:

  1. Off-by-one< vs <=, 0-indexed vs 1-indexed, slice boundaries
  2. Null/undefined — unchecked dereference, optional chaining gaps, missing defaults
  3. Race conditions — shared mutable state, async without await, missing locks
  4. Time-of-check/time-of-use — state changes between validation and use
  5. Integer overflow — arithmetic on user input, array index computation
  6. Unbounded loops — missing break conditions, user-controlled iteration counts
  7. Resource leaks — opened but not closed (files, connections, handles)
  8. Encoding — UTF-8 assumptions, byte vs character length, URL encoding
  9. Timezone — naive datetime comparisons, missing timezone conversion
  10. Comparison traps== vs ===, object equality, NaN, floating point
  11. Falsy traps0, "", "false" as valid values treated as falsy
  12. Async error paths — unhandled promise rejection, missing try/catch in async
  13. Concurrent writes — two processes writing same file/record without coordination

Process

  1. Read the diff.
  2. For each changed function, walk the full checklist.
  3. For each potential bug, write a concrete reproduction scenario.
  4. If you can't construct a reproduction, downgrade or drop the finding.
  5. Report findings with: category / severity / file / line / issue / reproduction / suggested fix.

What NOT to do

  • Do not report generic suspicions without reproduction scenarios.
  • Do not duplicate findings the code-reviewer would catch (naming, style).
  • Do not modify code.

Done when

Read the full file on GitHub · 56 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. 2d ago First seen · 56 lines · 39 tokens per session scan A 5ddbc621652f

Subscribe to this mod's changes

bug-auditor is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 23d ago), licensed MIT. It adds 39 tokens to every session and 537 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.

Related

Other agents, from other repositories

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

dynamic-agents

Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.

VoltAgent/voltagent · 0 tokens

langgraph

LangGraph is a framework for developing applications powered by language models. Integrating LangGraph with the Model Context Protocol (MCP) allows agents to utilize tools defined across one or more MCP servers, enabling seamless interaction with external data sources and services.

IBM/mcp-context-forge · 0 tokens

verify-agent

구현 완료 후 fresh-context 검증 전용. typecheck → lint → build → test 파이프라인 독립 실행. 단순 에러(import·타입) 자동 수정, 비수정 가능 에러 분류 보고. Use proactively — 비단순 코드 변경 완료 직후 사람 호출("검증해줘"·"빌드 확인")을 기다리지 말고 자율 spawn한다. 완료 주장 전 필수(verification.md 자율 검증 §11). 사람 발화에 의존하지 않는다. /handoff-verify 스킬에서도 자동 스폰. 구현 자체는 tdd-guide나 impl-worker 사용.

sangrokjung/claude-forge · 134 tokens

database-engineer

PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.

yonatangross/orchestkit · 28 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens