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.
npx agentmods add commands/hetcreep/coalmine/statsgit clone --depth 1 https://github.com/HetCreep/CoalMineWhat 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 | $0.00021 | $0.00548 |
| Opus 5 | $0.00010 | $0.00274 |
| Sonnet 5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
stats 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 3d 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
Produce the CoalMine stats report for this project, in the user's language. Three sections, tables only:
1. Canary activity (this session, from conversation context): | canary | runs | findings (C/H/M/L) | fixes accepted | Count every CoalMine canary invocation visible in this session (manual or hook-nudged). If none ran, one line saying so.
2. Rule freshness (scan now):
Grep the project's rules home (.claude/rules/, .agents/rules/, AGENTS.md) for coalmine: verified stamps. For each stamped rule:
| rule (file) | verified | revalidate | status |
Status = ✅ current · ⚠️ due within 7 days · ❌ OVERDUE.
To calculate the revalidation threshold (days) for each rule:
- If the stamp has
revalidate 30d(platform rule), checkplatformRuleRevalidateDaysfrom.coalmine.json(default: 30). - If the stamp has
revalidate 90d(general rule), checkruleRevalidateDaysfrom.coalmine.json(default: 90). If any rule is overdue, end by offering/gold-standardre-validation via AskUserQuestion (Run now / Queue / Skip). If no stamps exist, say the project has no CoalMine-filled rules yet.
3. Definitions freshness (the installed pattern DB):
Grep the installed CoalMine skills' references/*.md files for their coalmine: verified stamps (plugin cache or skills dir — wherever this skill itself is installed from). One line per file:
| definition file | verified | revalidate | status |
To calculate the revalidation threshold (days) for each definition file:
- If the stamp has
revalidate 30d(platform definition), checkplatformDefinitionRevalidateDaysfrom.coalmine.json(default: 30). - If the stamp has
revalidate 90d(general definition), checkdefinitionRevalidateDaysfrom.coalmine.json(default: 90). These ship with CoalMine itself — if any is OVERDUE, do NOT re-ground locally; advise updating CoalMine instead (claude plugin update coalmine@coalmineon Claude Code; reinstall viainstall.mjsfrom a fresh clone elsewhere), like updating antivirus definitions.
No prose beyond the tables and the single offer. Do not modify any file.
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.
- 3d ago First seen · 29 lines · 21 tokens per session scan A ea16bc8f8a0d
stats is a command published in the GitHub repository HetCreep/CoalMine (12 stars, last pushed 9d ago), licensed Apache-2.0. It adds 21 tokens to every session and 548 once invoked, about $0.0001 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 commands, from other repositories
upgrade
Upgrade the skillshare CLI binary and/or the built-in skillshare skill.
rust-features
Get Rust version changelog and new features.
diff
Compare two SKILL.md files section-by-section. Parses frontmatter and body sections independently, showing exactly what changed.
security
The security pass: secrets (blocking), SAST, dependency vulns — plus the index's entry points to review from.
init
Install the formatters this repository needs, with every command visible before it runs.
al
Run AgentLint diagnostic across all projects. Use when: user says /al, 'check all projects', 'agent lint', or '体检'.