bug-hunter

A specification-based bug-finding agent that compares acceptance criteria with the implementation and examines likely edge cases.

In plain words
What is it for?
Use it to review task implementations for null or undefined values, empty collections, boundary errors, race conditions, network failures, timeouts, and unclear requirements.
Why use it?
It helps expose missing behavior and bugs that appear only with unusual inputs, limits, failures, concurrency, or type conversions.

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/benrben/mpga/bug-hunter
Clone the repo
git clone --depth 1 https://github.com/benrben/MPGA
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 605 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 $0.00000 $0.00605
Opus 5 $0.00000 $0.00302
Sonnet 5 $0.00000 $0.00121
Haiku 4.5 $0.00000 $0.00060

Measured 2d ago against content hash 2cc85a5437cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-hunter 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.

docs/diagrams/agents/bug-hunter.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Hunter — The BEST Spec-Based Bug Detective, Nobody Finds Bugs Like Us

Workflow — The GREATEST Bug Hunt in History

flowchart TD
    A[Receive task with acceptance criteria — the MISSION] --> B[Read the spec FIRST — TREMENDOUS intel gathering]
    B --> C[Read the implementation code — let's see what they DID]
    C --> D[Trace logic for each acceptance criterion — TOTAL analysis]
    D --> E{Criterion fully implemented?}
    E -->|Yes| F[Mark as implemented — GREAT job]
    E -->|Partial| G[Flag as partial — NOT good enough]
    E -->|No code path found| H[Flag as GAP — WHERE IS IT? SAD!]
    F --> I[Hunt edge cases — this is where bugs HIDE]
    G --> I
    H --> I
    I --> J[Check null/undefined inputs — the SNEAKY ones]
    J --> K[Check empty collections — nobody checks these, but WE do]
    K --> L[Check boundary values / off-by-one — CLASSIC mistakes]
    L --> M[Check concurrent access / race conditions — very NASTY bugs]
    M --> N[Check error paths: network, file not found, timeout — Lock her up! the race condition!]
    N --> O[Check type coercion traps — JavaScript is TRICKY, folks]
    O --> P[Identify spec gaps: undocumented behavior, swallowed errors — the COVER-UP]
    P --> Q[Classify each finding — who can figure out this spaghetti?]
    Q --> R{"BUG: spec AND contradicting code cited?"}
    R -->|Yes| S["Label as BUG — CONFIRMED, we CAUGHT it"]
    R -->|No| T{"Code looks wrong but can't confirm?"}
    T -->|Yes| U["Label as RISK — needs INVESTIGATION"]
    T -->|No| V["Label as GAP — the spec LEFT IT OUT"]
    S --> W[Build spec coverage matrix — the FULL picture]
    U --> W
    V --> W
    W --> X[Produce bug hunt report with file:line evidence — TREMENDOUS detail]
    X --> Y[mpga spoke — if available]

Inputs — The Investigation Begins

  • Task acceptance criteria — from the GREATEST board ever built
  • Scope documents for the relevant modules — our INTELLIGENCE files
  • Implementation code under investigation — the SUSPECT
  • Test files — to check what IS and is NOT covered

Read the full file on GitHub · 49 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 · 49 lines · 0 tokens per session scan A 2cc85a5437cd

Subscribe to this mod's changes

bug-hunter is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 605 tokens. 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens