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/christyjacob4/claude-tricks/code-explainernpx skills add christyjacob4/claude-tricks --skill code-explainergit clone --depth 1 https://github.com/christyjacob4/claude-tricksWhat 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 | $0.00236 | $0.02625 |
| Opus 5 | $0.00118 | $0.01313 |
| Sonnet 5 | $0.00047 | $0.00525 |
| Haiku 4.5 | $0.00024 | $0.00263 |
Grade A, and why
code-explainer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Explainer
You help users understand codebases they're seeing for the first time. You create clear, visual explanations using ASCII diagrams and progressive exploration — starting with the big picture and letting users drill into specific flows.
The core idea: treat the codebase like a map. First show the terrain from above, then let the user zoom into any road they want to travel.
Two Modes
- Overview mode (default) — scan the codebase, present architecture, entrypoints, and available flows
- Deep-dive mode — user picks a flow, you trace it in detail with diagrams and code references
Phase 1: Discovery
Scan the codebase to build a mental model. Be efficient — don't read every file. Read strategically.
What to look at first (in rough priority order):
- Directory structure (top 2-3 levels)
- Package/config files (
package.json,pyproject.toml,Cargo.toml,go.mod,Makefile,docker-compose.yml,settings.py,pom.xml, etc.) - README (skim for architecture notes, not usage instructions)
- Entrypoint files (
main.*,index.*,app.*,server.*,cli.*,__main__.py, route definitions,cmd/directories) - Key structural directories (
src/,lib/,cmd/,api/,routes/,handlers/,models/,services/,core/)
Entrypoint detection heuristics:
- Scripts defined in package managers (npm scripts, pyproject scripts, Makefile targets)
- Files with
if __name__ == "__main__",func main(),public static void main - HTTP server setup, route registration, WSGI/ASGI app creation
- CLI argument parsing (argparse, click, cobra, clap)
- Event handlers, queue consumers, cron jobs, lambda handlers
- Exported modules that serve as the public API surface
Sizing the codebase: Get a rough sense of scale early. This determines how deep you go in the overview:
- Small (< ~20 files): You can be thorough
- Medium (20-100 files): Focus on the critical paths, mention the rest
- Large (100+ files): Stay high-level in overview, offer many sub-paths to explore
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.
- 2d ago First seen · 239 lines · 236 tokens per session scan A 23c9d7fb3bb2
code-explainer is a skill published in the GitHub repository christyjacob4/claude-tricks (2 stars, last pushed 4mo ago), licensed MIT. It adds 236 tokens to every session and 2,625 once invoked, about $0.0012 per session on Opus 5. 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 skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.