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/mse-online/farley_score_pluginWrote 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/commands/mse-online/farley_score_plugin/farley-score-coach)<a href="https://agentmods.dev/commands/mse-online/farley_score_plugin/farley-score-coach"><img src="https://agentmods.dev/badge/commands/mse-online/farley_score_plugin/farley-score-coach/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/commands/mse-online/farley_score_plugin/farley-score-coach"><img src="https://agentmods.dev/badge/commands/mse-online/farley_score_plugin/farley-score-coach.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 | $0.00013 | $0.07764 |
| Opus 5 | $0.00006 | $0.03882 |
| Sonnet 5 | $0.00003 | $0.01553 |
| Haiku 4.5 | $0.00001 | $0.00776 |
Grade B, and why
farley-score-coach scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Run: `PLUGIN_DIR=$(find ~/.claude/plugins -name "cli_calculator.py" 2>/dev/null | head -1 | sed 's|/lib/cli_calculator.py||')` How it starts
The opening of the file, as written. The whole thing — 882 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ENTRY POINT: Determine User Intent
CRITICAL: BEFORE doing anything else, determine how the user invoked this command.
If invoked WITH a specific topic or request
If the user's message includes a specific topic, question, or request (e.g., /msec:farley-score-coach help me understand maintainability, /msec:farley-score-coach practice tautologies, /msec:farley-score-coach review my test design), skip the welcome menu and go directly to the Farley Score Coach section below to begin coaching on that topic.
If invoked WITHOUT a specific topic
If the user simply typed /msec:farley-score-coach with no additional arguments, present the welcome menu.
Use the AskUserQuestion tool to present the menu. Do NOT output the options as plain text. This ensures the user gets a navigable interactive menu (arrow keys + Enter) rather than having to type a number.
Question: "Welcome to the Farley Score Coach! What would you like to learn?" Header: "Farley Score Coach"
Options (use these exact labels and descriptions):
- Label: "What is the Farley Score?" -- Description: "Understand the methodology, properties, and scoring system"
- Label: "Teach me the 8 Properties" -- Description: "Structured walkthrough with examples, easiest first"
- Label: "Practice with examples" -- Description: "Hands-on exercises using bundled sample tests"
- Label: "Let me explore" -- Description: "Open-ended coaching, you drive the conversation"
Option 1: What is the Farley Score?
Present a conversational explanation covering:
- Dave Farley identified 8 properties that make tests good -- not just passing, but well-designed
- The Farley Score measures these properties and produces a single number: the Farley Index (0-10)
- Properties have different weights: Understandable and Maintainable matter most (1.5x) because tests that read like specifications and survive refactoring have the most long-term value
- The key question the tool asks: "Would this test still pass if you deleted the production code?" If yes, it's a tautology -- a test that adds zero value
- The difference between test coverage (how much code runs) and test quality (how well the tests are designed) -- you can have 100% coverage with terrible tests
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.
- 10d ago First seen · 882 lines · 13 tokens per session scan B 2275949cd444
farley-score-coach is a command published in the GitHub repository mse-online/farley_score_plugin (27 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 7,764 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
pre-commit-full
Command: /pre-commit-full Purpose: Comprehensive pre-commit validation orchestrating all error prevention checks.
e2e
Generate comprehensive E2E tests for user workflows using Playwright.
snapshot
Generate and validate visual snapshots for UI components using Playwright.
validate
Full validation with specialized agents (post-change workflow).
test
Generate and run tests for file.
ui-validate
Validate UI component quality.