coalmine-scanner

coalmine-scanner is an agent for Claude Code from HetCreep/CoalMine. It costs 66 tokens per session (386 once invoked), scanned A, original, Apache-2.0.

A read-only scanning worker for CoalMine checks, assigned one code area and one type of problem at a time, and returns confirmed findings with file locations and evidence.

In plain words
What is it for?
Use it to scan code for a specific problem category, such as resource leaks or repeated database queries, and report the evidence for each finding.
Why use it?
It gives the larger review process focused, traceable results without changing files or mixing unverified suspicions with confirmed issues.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the coalmine plugin — 2 commands, 1 agent, 3 hooks, 1 plugin shipped together

Good fit Use it to scan code for a specific problem category, such as resource leaks or repeated database queries, and report the evidence for each finding.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hetcreep/coalmine/coalmine-scanner
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.

Clone the repo
git clone --depth 1 https://github.com/HetCreep/CoalMine

Made for: Claude Code.

Or install coalmine, the plugin that ships this one along with the rest of its 2 commands, 1 agent, 3 hooks, 1 plugin.

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 coalmine-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/hetcreep/coalmine/coalmine-scanner/github.svg)](https://agentmods.dev/agents/hetcreep/coalmine/coalmine-scanner)
Your own site
<a href="https://agentmods.dev/agents/hetcreep/coalmine/coalmine-scanner"><img src="https://agentmods.dev/badge/agents/hetcreep/coalmine/coalmine-scanner/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 coalmine-scanner

Your own site · 80×15
<a href="https://agentmods.dev/agents/hetcreep/coalmine/coalmine-scanner"><img src="https://agentmods.dev/badge/agents/hetcreep/coalmine/coalmine-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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.
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 $0.00066 $0.00386
Opus 5 $0.00033 $0.00193
Sonnet 5 $0.00013 $0.00077
Haiku 4.5 $0.00007 $0.00039

Measured 9d ago against content hash a50a665ecd0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

coalmine-scanner 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 9d 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/coalmine-scanner.md · 26 lines

What it actually says

You are a scan worker for a CoalMine canary skill. The orchestrator gives you ONE dimension (e.g. rot-canary category 5 "resource leaks", or scale-canary "N+1 queries") and a scope (files/dirs).

Rules:

  • READ-ONLY. Never edit, create, or delete files. Bash is for read-only commands only (build --dry checks, grep, language tooling in check mode).
  • CONFIRMED findings only — cite path:line plus the exact evidence (the absent catch, the call-site count, the unbounded append). Unverifiable suspicions go to a one-line SUSPECTED list, never the main table.
  • Trace reachability before calling anything dead or unused (reflection, DI, events, tests count as reachable).
  • Read the skill's references/*.md for per-stack detection procedures when told they exist.

Output — your ENTIRE final message is exactly this, nothing else:

| # | path:line | category | severity | finding | evidence |

then optional SUSPECTED: one-liners, then one line coverage: <what you scanned / skipped>.

Severity: CRITICAL (data loss/security/crash on normal path) · HIGH (real bug on reachable path) · MEDIUM (dead/dup/unwired) · LOW (style/doc rot). No preamble, no summary prose, no recommendations beyond the table's finding column.

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. 9d ago First seen · 26 lines · 66 tokens per session scan A a50a665ecd0f

Subscribe to this mod's changes

coalmine-scanner is an agent published in the GitHub repository HetCreep/CoalMine (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 66 tokens to every session and 386 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.