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/kirilxd/swe-interview-coach/coding-explaingit clone --depth 1 https://github.com/kirilxd/swe-interview-coachWhat 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 | $0.00040 | $0.01278 |
| Opus 5 | $0.00020 | $0.00639 |
| Sonnet 5 | $0.00008 | $0.00256 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade B, and why
coding-explain scanned grade B 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 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Explain entirely in chat — this is teach-first, not a graded run. Do **not** run any code in this command. You MAY offer to seed a scratch stub the user can try (e.g. point them at `/practice-coding <id>`), but explain r How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /coding-explain.
Step 1 — Resolve $ARGUMENTS
Take $ARGUMENTS as arg and resolve it to exactly one of four modes (check in this order):
- Pattern —
argmatches a pattern id in thecoding-frameworkstaxonomy (a### <pattern>sub-section under## Pattern taxonomy, e.g.two-pointers,sliding-window,dynamic-programming,backtracking,binary-search). Match on the slug OR the heading's key term — some ids map to compound headings (e.g.topological-sort→ the "Graph: topological sort" subsection;bfs/dfs/hashing/heapsimilarly cover their compound headings). Setmode = pattern. - Problem —
${CLAUDE_PLUGIN_ROOT}/library/coding/<arg>.mdexists (a library entry) OR$CLAUDE_PROJECT_DIR/coding/imported/<arg>.mdexists (an imported entry; also strip a leadingimported/fromargand retry, so both<id>andimported/<id>resolve). Read it and hold its full content astopic_source. Setmode = problem. - Free prompt —
argis non-empty but matches neither a pattern nor an entry. Hold it verbatim astopic_prompt. Setmode = free. - Empty —
argis empty. Setmode = list.
If mode = list: load the coding-frameworks skill and list every ### <pattern> from its ## Pattern taxonomy; then Read the frontmatter id and difficulty of each ${CLAUDE_PLUGIN_ROOT}/library/coding/*.md and present the problems as a numbered list grouped by difficulty. Ask the user to pick a pattern or a problem, then re-resolve their answer through this step.
Step 2 — Load the skill
Before teaching anything, load the coding-frameworks skill (the UMPIRE method, the pattern taxonomy, the Big-O cheatsheet, Python idioms). It grounds every walkthrough below and is never read aloud verbatim.
Step 3 — Teach in chat
Explain entirely in chat — this is teach-first, not a graded run. Do not run any code in this command. You MAY offer to seed a scratch stub the user can try (e.g. point them at /practice-coding <id>), but explain runs nothing itself.
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 · 62 lines · 40 tokens per session scan B d3d3138a2a2a
coding-explain is a command published in the GitHub repository kirilxd/swe-interview-coach (79 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,278 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
mock
A complete simulated interview (4-6 questions in sequence) with holistic feedback on the full arc — not just individual answers.
review
View your learning progress — quiz scores, weak areas, and what to study next.
start-1-7
Start Lesson 1.7 - Project Memory.
edit-textbook-chapter
Edit a textbook-style chapter, following evidence-based writing instructions.
onboard
This command acts as an expert technical mentor to help you rapidly understand a new codebase, generating a comprehensive "Survival Guide" for the project.
start-1
Claude Code 를 처음 쓰는 PM 이 "설치 → 도구 지도 이해 → CLAUDE.md 로 맥락 주기" 까지 직접 손으로 해보며 익히도록, 한 번에 한 단계씩 끌고 간다.