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.
git clone --depth 1 https://github.com/HetCreep/CoalMineWrote 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.
[](https://agentmods.dev/agents/hetcreep/coalmine/coalmine-scanner)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:lineplus 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/*.mdfor 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.
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.
- 9d ago First seen · 26 lines · 66 tokens per session scan A a50a665ecd0f
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.
Other agents, from other repositories
verifier
Fresh-eyes, coverage-first quality judge for sweep passes on any deliverable (code, UI, copy, video frames, research, prompts). Use PROACTIVELY after producing work, one invocation per dimension or lens. Give it the rubric (or the craft file path), the evidence (file paths, screenshot paths, run output), and the lens…
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
agent-reviewer
Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.
code-verifier
Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.
strict-reviewer
Strict code reviewer. Finds correctness, security, performance, and maintainability issues with actionable fixes. Use proactively after code changes.
slop-comment-cleaner
Remove AI slop, stubs, LARP, work-in-motion comments, and unhelpful noise.