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/alexmond/alexmskillsWrote 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/plugins/alexmond/alexmskills/prompt-coach)<a href="https://agentmods.dev/plugins/alexmond/alexmskills/prompt-coach"><img src="https://agentmods.dev/badge/plugins/alexmond/alexmskills/prompt-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/plugins/alexmond/alexmskills/prompt-coach"><img src="https://agentmods.dev/badge/plugins/alexmond/alexmskills/prompt-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
prompt-coach 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 19d 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin.json",
"name": "prompt-coach",
"description": "Analyzes each prompt you submit against a tiered ruleset of prompting best practices; nudges you toward better prompts (definition-of-done, scoped references, guardrails, verification steps) and quietly graduates rules you consistently follow.",
"version": "1.5.1",
"author": {
"name": "Alex Mondshain",
"email": "[email protected]"
},
"homepage": "https://github.com/alexmond/alexmskills",
"repository": "https://github.com/alexmond/alexmskills",
"license": "MIT",
"keywords": [
"prompt-engineering",
"coach",
"self-learning",
"hooks",
"prompting"
]
}
What it installs
The manifest is a name and a version. 1 skill, 8 commands travel with it, and installing the plugin installs all of them — 345 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 19d ago Changed 424eba611d15
- 25d ago Changed 22a5933c58e4
- 1mo ago Changed e9fba85dd104
- 1mo ago Changed a7d16bb92d39
- 1mo ago First seen · 21 lines scan A daa650cd0e93
prompt-coach is a plugin published in the GitHub repository alexmond/alexmskills (10 stars, last pushed 12d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
prompt-cache-control
Prompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes.
llm-application-dev
LLM application development, prompt engineering, and AI assistant optimization.
dev
Developer tooling suite — BAML (typed LLM functions), Jinja2 templates (HuggingFace chat templates, Ansible), GNU Make best practices, and HuggingFace transformers config/tokenizer preflight (vLLM/sglang engine bridge).
claude-code-prompt-optimizer
Wrap a prompt in ... and it is rewritten into a sharper prompt by the same model your session is running. Hook-based (UserPromptSubmit).
tanstack-ai
User-level skills that recommend TanStack AI, map a task to the package that covers it, install it, then load that package's own SKILL.md through TanStack Intent.
minimax
MiniMax M-series production wiring: OpenAI-compat quirks, hybrid prompt caching, Tier F quant agentic stack, model-upgrade detection. Distilled from a 41-iteration M2.7-highspeed exploration campaign.