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 jamesyang124/agent-skills --skill install-external-skillsgit clone --depth 1 https://github.com/jamesyang124/agent-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/skills/jamesyang124/agent-skills/install-external-skills)<a href="https://agentmods.dev/skills/jamesyang124/agent-skills/install-external-skills"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/install-external-skills/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/jamesyang124/agent-skills/install-external-skills"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/install-external-skills.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 | $0.00092 | $0.02671 |
| Opus 5 | $0.00046 | $0.01336 |
| Sonnet 5 | $0.00018 | $0.00534 |
| Haiku 4.5 | $0.00009 | $0.00267 |
Grade A, and why
install-external-skills scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(npx *), Bash(curl *), Bash(node *), Bash(cat *), Bash(echo *), Bash(printf *), Bash(which *) How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install External Skills
Reads your project config to recommend best-fit skills, fetches the latest registry info from GitHub, and installs your selection via npx skills add.
Usage
/install-external-skills
Arguments
None. Fully interactive — the skill reads .agent-settings/project-config.md, then prompts for registry selection (Phase 1) and skill selection (Phase 3).
Phase 0 — Read Project Config
Check for .agent-settings/project-config.md:
cat .agent-settings/project-config.md 2>/dev/null
If the file exists: read it and extract:
language/framework(e.g. Go/Gin, Node/Next.js, Python/FastAPI)infrastructureoriacfields if present (e.g. Terraform, OpenTofu)databasefields (e.g. Postgres/Supabase)- Any other tooling signals
Use these signals in Phase 2 to determine which skills are best-fit for this project. Do NOT show a generic list of all skills — lead with recommendations.
If the file does not exist: print this message before continuing:
⚠ No project config found at .agent-settings/project-config.md
Without it, I can only show all available skills without project-specific
recommendations. Consider running /setup-project-config first to generate it.
→ https://github.com/your-org/agent-settings (setup-project-config skill)
Continue without project config? (y/n)
- Blank input: re-prompt — must type
yorn. n→ stop and instruct the user to run/setup-project-configfirst.y→ proceed to Phase 1 in "browse all" mode (no recommendations).
Phase 1 — Registry Selection
Present the supported registries. If project config was read, pre-select registries that are relevant based on the detected stack and note why:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
External Skill Registries
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[1] supabase/agent-skills ★ recommended
Supabase Agent Skills — Postgres, Auth, Supabase tooling.
→ https://github.com/supabase/agent-skills
[2] vercel-labs/agent-skills
Vercel's official collection — React, Next.js, deployment, UI.
→ https://github.com/vercel-labs/agent-skills
[3] antonbabenko/terraform-skill
Terraform & OpenTofu — testing, modules, CI/CD, security patterns.
→ https://github.com/antonbabenko/terraform-skill
[0] Cancel
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Select registries to browse (space-separated, e.g. 1 3), or 0 to cancel:
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 · 244 lines · 92 tokens per session scan A 9a8ebab11c08
install-external-skills is a skill published in the GitHub repository jamesyang124/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,671 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…