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 commands/dykyi-roman/awesome-claude-code/explaingit clone --depth 1 https://github.com/dykyi-roman/awesome-claude-codeWrote 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/commands/dykyi-roman/awesome-claude-code/explain)<a href="https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/explain"><img src="https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/explain.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01791 |
| Opus 5 | $0.00024 | $0.00896 |
| Sonnet 5 | $0.00010 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
explain 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 today.
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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Explain Command
Explain code structure, business logic, data flows, and architecture patterns for any scope — from a single file to an entire project, HTTP route, or console command.
Input Parsing
Parse $ARGUMENTS to extract input, mode, and optional meta-instructions:
Format: <input> [mode] [-- instructions]
Arguments:
- input: File, directory, ".", HTTP route, or console command (required)
- mode: quick|deep|onboarding|business|qa (optional, auto-detected)
- -- instructions: Focus area or specific question (optional)
Input types (auto-detected):
1. HTTP route: GET /api/orders
2. HTTP route: POST /api/orders/{id}/status
3. Console cmd: app:process-payments
4. Console cmd: import:products
5. File path: src/Domain/Order/Order.php
6. Directory: src/Domain/Order/
7. Project root: .
Examples:
- /acc:explain GET /api/orders
- /acc:explain POST /api/orders/{id}/status deep
- /acc:explain app:process-payments
- /acc:explain import:products -- explain data transformation pipeline
- /acc:explain src/Domain/Order/Order.php
- /acc:explain src/Domain/Order/
- /acc:explain . onboarding
- /acc:explain src/Payment business
- /acc:explain src/Domain/Order/ deep -- focus on state transitions
- /acc:explain . qa -- how does payment processing work?
Parsing rules:
- Split
$ARGUMENTSby--(space-dash-dash-space) - First part = input + optional mode, Second part = meta-instructions
- Check if last word of first part is a valid mode (
quick|deep|onboarding|business|qa) - If valid mode found, extract it; everything else is the input
- If no mode specified, auto-detect based on input type
Input Type Detection
Before path validation, detect input type from the parsed input:
- If input matches
^(GET|POST|PUT|PATCH|DELETE|HEAD|OPTIONS)\s+/→input_type = "route" - If input matches
^[a-z][a-z0-9_-]*:[a-z][a-z0-9:_-]*$→input_type = "command" - If
test -f input→input_type = "file" - If
test -d input→input_type = "directory" - If input = "." →
input_type = "project" - Otherwise → report error: "Invalid input. Provide a file/directory path, HTTP route (GET /path), or console command (namespace:name)."
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.
- today First seen · 217 lines · 0 tokens per session scan A 6a6e2229c7bc
explain is a command published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 19d ago), licensed MIT. It adds 49 tokens to every session and 1,791 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".
setup-bigquery.es
Command "setup-bigquery.es" from minicoohei/ai-agent-camp, covering configuración de autenticación bigquery / gcp, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: instalación de gcloud cli.
setup-content
Lesson command — 教材コンテンツの初回セットアップ.