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 skills/hetcreep/coalmine/source-groundingnpx skills add HetCreep/CoalMine --skill source-groundinggit 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/skills/hetcreep/coalmine/source-grounding)<a href="https://agentmods.dev/skills/hetcreep/coalmine/source-grounding"><img src="https://agentmods.dev/badge/skills/hetcreep/coalmine/source-grounding.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.02228 |
| Opus 5 | $0.00037 | $0.01114 |
| Sonnet 5 | $0.00015 | $0.00446 |
| Haiku 4.5 | $0.00007 | $0.00223 |
Grade A, and why
source-grounding 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Grounding
Language: Generate EVERYTHING at runtime in the user's language — questions, answer options, menu labels, recommendations, report narrative. Detect from their messages; never default to English just because this file is English. English is allowed only for technical terms: commands, paths, code identifiers, severity labels (CRITICAL/HIGH/MEDIUM/LOW), and tier names (Light/Standard/Heavy).
Config reads — every config key, always the CASCADE, never the bare project file: ~/.claude/.coalmine.json first, then the project config (own agent dir → other known agent dirs → legacy <gitroot>/.coalmine.json), project wins per key. A bare project read is ABSENT on a machine configured only globally, so it silently yields defaults.
Standing rule — active every response. No invocation needed for routine use.
Consent gates (G1–G4, declared)
| # | what it gates | when it fires | Agent lane | Hook lane |
|---|---|---|---|---|
| G1 | model tier | before work starts | ask_question, 3 tiers, wait for pick |
suppressed — auto-Light, no tier question |
| G2 | how to proceed on an unfetchable source | source can't be fetched, user present | ask_question |
ask_question |
| G3 | entanglement hand-off | after the findings, cross-domain | ask_question, once |
ask_question, once |
| G4 | self error-report | skill misbehaves | offer, never auto-submit | offer, never auto-submit |
Hook cells assume an interactive session (G2–G4 need a user to answer); non-interactive Hook fires D1 instead of G2, and offers nothing for G3/G4.
What to verify (not memory)
- CRITICAL (always fetch or flag — P2): API/SDK call signatures · library versions & deprecations · CVEs/security advisories · auth/crypto specs · LLM model IDs & params
- MEDIUM (verify when unsure): package names · config keys · CLI flags · protocol specs
- LOW/stable: math, algorithms, language syntax → memory fine (P3)
How
- Identify the version-sensitive claim.
- Name the authoritative source (official docs, advisory DB, package registry, spec, source code).
- Fetch (WebSearch/WebFetch/docs MCP) — or flag
⚠️ unverified: check [source](D1). - Cite at CRITICAL/MEDIUM. Don't over-verify stable facts (P3).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +2 lines 69373df43f59
- 5d ago First seen · 101 lines · 74 tokens per session scan A a321db7dced9
source-grounding is a skill published in the GitHub repository HetCreep/CoalMine (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 74 tokens to every session and 2,228 once invoked, about $0.0004 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 skills, from other repositories
flockion_engineering_ai
Forces the simplest, shortest, safest AI solution that actually works. Lazy senior-engineer pragmatism for LLM features, agents, RAG, tool-calling, and prompts. Use a prompt before a chain, retrieval before fine-tuning, deterministic code before an agent, and one tool before a tool framework. Keep critical business…
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
developing-genkit-js
Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.
agent-platform-prompt-management
Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…