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/sethdford/claude-skillsWrote 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/sethdford/claude-skills/decision-making)<a href="https://agentmods.dev/plugins/sethdford/claude-skills/decision-making"><img src="https://agentmods.dev/badge/plugins/sethdford/claude-skills/decision-making/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/sethdford/claude-skills/decision-making"><img src="https://agentmods.dev/badge/plugins/sethdford/claude-skills/decision-making.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
decision-making 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 1mo 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
{
"name": "decision-making",
"version": "1.0.0",
"description": "Master architectural decision-making: ADRs, technology selection, build-vs-buy analysis, proof of concepts, and migration planning.",
"author": { "name": "Seth Ford" },
"keywords": [
"architect",
"decisions",
"adr",
"technology-selection",
"migration"
],
"license": "MIT"
}
What it installs
The manifest is a name and a version. 8 skills, 3 commands travel with it, and installing the plugin installs all of them — 212 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill architecture-decision-record A 23 tokens
- Skill build-vs-buy A 29 tokens
- Skill technology-radar A 23 tokens
- Skill legacy-modernization A 25 tokens
- Skill migration-strategy A 25 tokens
- Skill proof-of-concept-plan A 20 tokens
- Skill risk-assessment A 16 tokens
- Skill vendor-evaluation A 19 tokens
- Command evaluate-technology A 11 tokens
- Command make-decision A 13 tokens
- Command plan-migration A 8 tokens
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.
- 1mo ago First seen · 15 lines scan A 374accb72c42
decision-making is a plugin published in the GitHub repository sethdford/claude-skills (44 stars, last pushed 7mo 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 2026-08-30.
Other plugins, from other repositories
skills
Modern Deno development knowledge: dependency management, npm and JSR packages, permissions, the built-in toolchain, migrating from Node/npm/yarn/pnpm/bun, Fresh, and Deno Deploy.
pragma
Deterministic linting hooks, semantic code validators, and a multi-LLM advisory council. Enforces coding rules mechanically — not by suggestion.
peer-model
Run any Anthropic-compatible model (DeepSeek, GLM, ...) as a peer Claude Code session: optionally fork the current conversation context, then exchange messages via SendMessage. Profiles live in /.config/cc-peer-model/config.toml.
ceo-skill
Intelligent project management dashboard - view all projects status, priorities, and todos from a CEO perspective.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.