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 agentmods add skills/secondlifes/code-intel/rad-skill-findernpx skills add SecondLifes/code-intel --skill rad-skill-findergit clone --depth 1 https://github.com/SecondLifes/code-intelWhat 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 | $0.00179 | $0.05232 |
| Opus 5 | $0.00089 | $0.02616 |
| Sonnet 5 | $0.00036 | $0.01046 |
| Haiku 4.5 | $0.00018 | $0.00523 |
Grade C, and why
rad-skill-finder scanned grade C 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 yesterday.
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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
hidden instructions, credential/secret requests, instructions to send data to external URLs, and obfuscated/suspicious commands. This is a copy
100% identical to rad-skill-finder — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Finder
When to use
Check here before writing any non-trivial capability from scratch — even one you're confident you already know how to do. Confidence isn't the bar; "does a maintained skill already exist for this" is. This was learned the hard way: the first live test of this workflow asked for a GitHub repo clone/update script, and the capability got written from general knowledge without this skill ever being consulted — exactly the case it exists to prevent.
Concrete triggers:
- Any task in a domain with well-known best practices beyond basic syntax — git/GitHub automation, web frontend (HTML/CSS/JS/Bootstrap, visual/UI design), CI/CD, cloud APIs, database access patterns, and similar. "I already know how to do this" is not a reason to skip the check.
rad-template-buildersearching for a relevant skill for a new template (this skill's main caller).- User asks "is there a skill for this?" or describes a capability without knowing whether it exists as a skill.
- Adding new capability to an existing template, before rewriting the same content from scratch.
Not every trivial action needs a full search (reading a file, running an existing command) — the bar is "non-trivial capability," not "every single action." See Known Good Picks below for common gaps that skip straight to a verified answer without running the full search order.
Scope — skills, plugins, AND MCP servers
The search target is not just Agent Skills. A capability gap can be closed by any of three resource types, and all three are in scope:
- Skills (
SKILL.md-shaped) — the primary target; the search order below is written for these. - Plugins (Claude Code plugin marketplaces, tool-specific extension ecosystems) — check when the gap is tooling/workflow-shaped rather than knowledge-shaped.
- MCP servers — check when the gap is live-data/external-system
access (APIs, databases, SaaS products). Sources: the official MCP
registry search (
search_mcp_registrytool where available),github.com/modelcontextprotocol/servers, andmcpservers.org-style directories.
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.
- yesterday First seen · 405 lines · 179 tokens per session scan C bd79060d3048
rad-skill-finder is a skill published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 179 tokens to every session and 5,232 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). It is 100% identical to rad-skill-finder, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…