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 skills add YoungLeadersDotTech/young-leaders-tech-marketplace --skill ground-truth-templategit clone --depth 1 https://github.com/YoungLeadersDotTech/young-leaders-tech-marketplaceWrote 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/youngleadersdottech/young-leaders-tech-marketplace/ground-truth-template)<a href="https://agentmods.dev/skills/youngleadersdottech/young-leaders-tech-marketplace/ground-truth-template"><img src="https://agentmods.dev/badge/skills/youngleadersdottech/young-leaders-tech-marketplace/ground-truth-template/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/skills/youngleadersdottech/young-leaders-tech-marketplace/ground-truth-template"><img src="https://agentmods.dev/badge/skills/youngleadersdottech/young-leaders-tech-marketplace/ground-truth-template.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 | $0.00043 | $0.02314 |
| Opus 5 | $0.00022 | $0.01157 |
| Sonnet 5 | $0.00009 | $0.00463 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
ground-truth-template 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Justification: pure template scaffold - emits verbatim template content with no LLM reasoning pass.
Ground Truth Documentation Template
Purpose
This template guides the creation of ground truth skills - verifiable, canonical reference documentation that provides definitive facts, definitions, and validation criteria. Replace all [PLACEHOLDER] values with actual verified information.
SKILL.md Frontmatter Template
---
name: [project]-[domain]-ground-truth
description: Ground truth documentation for [PROJECT_NAME] [DOMAIN] providing canonical definitions, verified facts, and validation criteria. Auto-invoke when user discusses [TOPIC_1], [TOPIC_2], or validates [VALIDATION_SCENARIO]. Do NOT load for general [DOMAIN] discussions without [PROJECT_NAME] context.
disable-model-invocation: true
allowed-tools: []
version: 1.0.0
category: Ground Truth
tags: [[project], [domain], reference, validation]
source: [CANONICAL_SOURCE_URL_OR_LOCATION]
verified-date: [YYYY-MM-DD]
next-review: [YYYY-MM-DD]
---
Description Engineering Guidance:
✅ DO include:
- Specific topics covered (definitions, metrics, processes)
- Validation scenarios where ground truth applies
- Canonical source attribution
- Version or release reference if applicable
❌ DON'T use:
- Generic descriptions ("Provides information about...")
- No source attribution
- No scope boundaries (will load for irrelevant discussions)
Example Good Description:
Ground truth documentation for Apollo payment processing providing canonical transaction states, error codes, and retry policies. Auto-invoke when user discusses payment flows, error handling, or validates transaction logic. Do NOT load for general payment discussions outside Apollo.
Ground Truth Content Structure
1. Canonical Definitions
Purpose: Single source of truth for terms, concepts, and classifications
Term: [TERM_NAME]
Definition: [PRECISE_CANONICAL_DEFINITION]
Source: [AUTHORITATIVE_SOURCE] (verified [DATE])
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.
- 12d ago First seen · 279 lines · 43 tokens per session scan A e454062d4879
ground-truth-template is a skill published in the GitHub repository YoungLeadersDotTech/young-leaders-tech-marketplace (10 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 2,314 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
shared-patterns
Provide reusable patterns for validation, error handling, scaffolding. Use for skill consistency.
rule-creator
Create production-ready v3.0 Cursor rule files by orchestrating template generation, schema validation, and RULESINDEX.md indexing. Triggers on keywords like "create rule", "add rule", "new rule", "generate rule". Supports Python, Snowflake, JavaScript, Shell, Docker, Golang domains (000-999 range).
merge-seed
Merge upstream React Starter Kit updates (the seed remote) into main, preserving this project's identity, scope, and behavior. Use when asked to sync, pull, or merge the seed / starter kit / upstream template.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
portaljs-check-data-quality
Audit a local or remote tabular file (CSV/TSV) for common data quality issues — schema, nulls, types, duplicates. Read-only. Use when a dataset needs a quality check before publishing, or a showcase renders wrong (blank cells, garbled numbers, an unsortable date column) and the cause needs isolating.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.