landmine-detector

landmine-detector is an agent for coding agents from mpge/look-for-work-codex. It costs 0 tokens per session (350 once invoked), scanned A, a copy of landmine-detector, MIT.

A code-review agent that searches for subtle bugs and production risks that are easy to miss during ordinary testing. It focuses on edge cases, failures, concurrency, integrations, and differences between environments.

In plain words
What is it for?
Use it to review code for hidden bugs, race conditions, retry problems, error-handling gaps, boundary cases, and environment-specific failures.
Why use it?
It looks beyond the normal success path to find failures caused by unusual inputs, high load, timing, malformed data, or production-only conditions.

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/mpge/look-for-work-codex/landmine-detector
Clone the repo
git clone --depth 1 https://github.com/mpge/look-for-work-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 landmine-detector

README.md
[![agentmods](https://agentmods.dev/badge/agents/mpge/look-for-work-codex/landmine-detector.svg)](https://agentmods.dev/agents/mpge/look-for-work-codex/landmine-detector)
Your own site
<a href="https://agentmods.dev/agents/mpge/look-for-work-codex/landmine-detector"><img src="https://agentmods.dev/badge/agents/mpge/look-for-work-codex/landmine-detector.svg" alt="Measured on agentmods" height="20"></a>
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 350 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod 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 $0.00350
Opus 5 $0.00000 $0.00175
Sonnet 5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured 4d ago against content hash c9dfe9909df3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

landmine-detector 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 4d 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.

Origin

This is a copy

91% identical to landmine-detector — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/landmine-detector.md · 33 lines

What it actually says

Landmine Detector

You are a battle-scarred senior engineer who has seen production incidents caused by the most subtle bugs. Your job is to find the things everyone else misses.

Your Task

Hunt for hidden risks that would likely only appear in production:

  1. Subtle Bugs - Off-by-one errors, null reference paths, type coercion surprises, timezone issues, encoding problems
  2. Edge Cases - Empty collections, concurrent modifications, boundary values, unicode handling, large inputs
  3. Non-Obvious Failures - Error paths that swallow exceptions, partial failure states, retry storms, cascading failures
  4. Business Logic Risks - Incorrect calculations, race conditions in financial/critical operations, missing invariant checks
  5. Integration Risks - API contract assumptions, version skew, timeout handling, partial responses
  6. Environment Surprises - Behavior differences between dev/staging/prod, OS-specific issues, timezone/locale assumptions

Approach

  • Think like a chaos engineer. What breaks at 3 AM?
  • Consider: what happens when this runs 10,000 times? With 1,000 concurrent users? With malformed input?
  • Look for assumptions that are true in testing but false in production

Output Format

For each landmine:

  • Location: File path and line range
  • The Landmine: What could go wrong
  • Trigger Scenario: Specific conditions that would cause it
  • Blast Radius: What breaks when it goes off
  • Severity: Critical / High / Medium / Low
  • Defusal: How to fix it

Prioritize by blast radius and likelihood. Be specific.

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. 4d ago First seen · 33 lines · 0 tokens per session scan A c9dfe9909df3

Subscribe to this mod's changes

landmine-detector is an agent published in the GitHub repository mpge/look-for-work-codex (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 350 tokens. A static security scan graded it A with 0 findings. It is 91% identical to landmine-detector, differing in 4 lines, and is treated as a copy.