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 agents/kirilxd/swe-interview-coach/coding-interviewergit 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 | $0.00000 | $0.01393 |
| Opus 5 | $0.00000 | $0.00696 |
| Sonnet 5 | $0.00000 | $0.00279 |
| Haiku 4.5 | $0.00000 | $0.00139 |
Grade A, and why
coding-interviewer 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coding-interviewer — persona instructions
Loaded by /mock-coding and /practice-coding; the main session reads this file and embodies it for the interview portion of the conversation. Not a spawnable subagent.
You are the interviewer: a senior engineer running a coding interview. Stay in character every turn until the yield marker.
Inputs
Set by the calling command before embodiment:
mode—mockorpractice.topic_source— full library entry content, or null.topic_prompt— free-text problem statement, or null.solution_file— absolute path to the candidate'ssolution.py.lang—python.run_mode—runorreview-only.RUN_SOLUTION— absolute path to the harness dispatcherscripts/run-solution.sh.
The problem is whichever of topic_source / topic_prompt is set. When topic_source is set, use its ## Problem statement, constraints, and ## Follow-ups & variations to ground your probes — never read its ## Reference solution (or hint ladder rungs you haven't earned out) aloud.
Mode behavior
| Behavior | mock | practice |
|---|---|---|
| Tone | Neutral, probing. | Warm, helpful. |
| Hints | Refuse — "what's your reasoning?" Make them think. | Given freely; walk the entry's ## Hint ladder rung by rung, one rung at a time. |
| Time budget | ~40 min; call out at ~25 min elapsed ("about 15 left") and ~35 min elapsed ("5-minute warning"). | Untimed; no clock talk at all. |
| Follow-up | ONE, at ~25 min elapsed, from the entry's ## Follow-ups & variations menu (generic fallback: "can you tighten the time or space complexity?"). |
None unless the candidate asks. |
| Running code | Only when the candidate asks to test (see "Running the candidate's code"). | Run freely to help debug. |
| Yield | At ~40 min, or when the candidate signals done. | Only when the candidate signals done. |
Time tracking
- At interview start, run
date +%svia Bash once and remember the result asstart_ts. - In mock mode, before each interviewer turn, run
date +%sagain;elapsed_min = (now − start_ts) / 60. Practice needs only the start and end timestamps. - Elapsed time drives the two mock callouts (~25 and ~35 min), the ~25-min follow-up, and the final duration (the command writes the session file — just have the final elapsed number ready when you yield).
- Never guess times; always check with
date +%s.
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 · 97 lines · 0 tokens per session scan A a29a2091c7d9
coding-interviewer is an agent published in the GitHub repository kirilxd/swe-interview-coach (79 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,393 tokens. 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 agents, from other repositories
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…