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-importgit 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 | $0.00032 | $0.01439 |
| Opus 5 | $0.00016 | $0.00720 |
| Sonnet 5 | $0.00006 | $0.00288 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
coding-import 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /coding-import. You import a single LeetCode problem into the user's local library as a normal markdown entry, using only the WebFetch tool — no MCP server, no login, no auth, no submission, and no redistribution beyond the user's own machine. This is a read-only fetch of a public problem page for personal interview prep.
Step 1 — Parse $ARGUMENTS
Resolve $ARGUMENTS into a slug and a fetch target:
- A full URL like
https://leetcode.com/problems/<slug>/→ extract<slug>(the path segment afterproblems/); fetch target is that URL. - A bare slug like
two-sum(kebab-case, no slashes) →slug = <arg>; fetch target ishttps://leetcode.com/problems/<slug>/. - The literal
daily→ fetch target is the daily endpoint (Step 2);slugis not yet known and is filled in from the fetched title.
If $ARGUMENTS is empty, ask the user for a URL, slug, or daily, then stop until they answer.
Step 2 — Fetch with WebFetch
Fetch the problem with the WebFetch tool (the same tool the behavioral commands use) — no auth header, no cookies, no login.
- Primary (URL/slug):
WebFetchthehttps://leetcode.com/problems/<slug>/page. Prompt it to extract: title, difficulty (Easy/Medium/Hard), the full problem statement, every worked example (input → output, plus any explanation), the constraints, and the function name + parameters if a code signature is shown. - Fallback (extraction poor — LeetCode is JS-heavy, so the page often renders thin): if the primary fetch returns little or no statement/examples,
WebFetchthe unofficial REST endpoint instead, which returns JSON:- URL/slug:
https://alfa-leetcode-api.onrender.com/select?titleSlug=<slug> daily:https://alfa-leetcode-api.onrender.com/daily— then setslugfrom the returnedtitleSlug. Extract the same fields from the JSON (question/contentHTML → statement + examples + constraints;difficulty;title).
- URL/slug:
- Both fail / empty: do NOT invent a problem — ask the user to paste the problem text (statement + examples + constraints) and build from that; if they decline, stop.
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.
- 3d ago First seen · 87 lines · 32 tokens per session scan A ad71631343ca
coding-import is a command published in the GitHub repository kirilxd/swe-interview-coach (79 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,439 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 2026-08-30.
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.