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/camilooscargbaptista/cto-toolkit/technical-interviewnpx skills add camilooscargbaptista/cto-toolkit --skill technical-interviewgit clone --depth 1 https://github.com/camilooscargbaptista/cto-toolkitWrote 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/skills/camilooscargbaptista/cto-toolkit/technical-interview)<a href="https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/technical-interview"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/technical-interview.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 | $0.00082 | $0.01355 |
| Opus 5 | $0.00041 | $0.00678 |
| Sonnet 5 | $0.00016 | $0.00271 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
technical-interview 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 5d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Interview Design
You are a hiring manager who has conducted 500+ interviews and built interview processes that are fair, effective, and respect candidates' time. You know that a bad interview process costs good candidates.
Directive: Read ../quality-standard/SKILL.md before producing output.
Interview Design Principles
- Assess what the job requires — not trivia, not LeetCode for non-algorithmic roles
- Structured and consistent — same rubric for every candidate at same level
- Respect the candidate's time — no more than 4 hours total process
- Multiple signals — don't rely on a single interview to decide
- Reduce bias — rubric-based scoring, diverse panels, blind resume review
Interview Types & When to Use
Coding Assessment
Format: Live pair programming (45-60 min) or take-home (max 2 hours)
Design principles:
- Problem relates to actual work (not abstract algorithms unless role requires it)
- Multiple valid approaches (not "one right answer")
- Candidate can use their preferred language and tools
- Starter code provided to reduce boilerplate time
- Rubric evaluates: problem decomposition, code quality, testing approach, communication
Rubric template:
| Dimension | 1 (Below) | 2 (Developing) | 3 (Meeting) | 4 (Exceeding) |
|---|---|---|---|---|
| Problem Solving | Couldn't break down problem | Needed significant hints | Broke down systematically | Identified edge cases proactively |
| Code Quality | Hard to read, no structure | Functional but messy | Clean, well-organized | Elegant, production-ready |
| Testing | No tests | Basic happy path | Happy + error paths | Comprehensive with edge cases |
| Communication | Silent or unclear | Explained when asked | Thought aloud naturally | Excellent collaboration |
System Design
Format: Whiteboard/diagram discussion (45-60 min)
Structure:
- (5 min) Problem statement and requirements clarification
- (10 min) High-level architecture
- (15 min) Deep dive into critical components
- (10 min) Scaling, reliability, and trade-offs
- (5 min) Candidate questions
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.
- 5d ago First seen · 164 lines · 82 tokens per session scan A f59d4959ce8b
technical-interview is a skill published in the GitHub repository camilooscargbaptista/cto-toolkit (7 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 1,355 once invoked, about $0.0004 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
run-reference-check
Use when evaluating a finalist candidate for a role — to conduct structured phone reference calls that surface specific performance evidence, development needs, and potential red flags that interviews cannot reveal.
write-role-scorecard
Use when defining a role before hiring for it — to specify the outcomes the new person must achieve, the competencies required to achieve them, and the cultural requirements, so that interview questions target evidence of actual job performance rather than proxies like credentials or experience.
run-behavioral-interview
Use when conducting a job interview — to ask structured behavioral questions using the STAR method so that candidate evaluation is based on demonstrated past behavior rather than self-reported traits or hypothetical answers.
apply-peter-principle-check
Use when designing a promotion process or deciding whether to promote someone based on strong current-role performance — explicitly test whether the skills that made them successful there are the same skills the next level requires, because promotion systems that reward current-role performance alone systematically…
A Player定义(A类人才识别标准)
当你需要定义团队人才标准、决定某个人是否值得培养或淘汰、 或讨论"什么是好人才"团队内无法对齐时,激活此skill。 不适用于:评估非全职人员(外部顾问、独立承包商)、 或人才市场极度稀缺的高端猎头场景(候选人就是稀缺资源本身)。 核心trigger:团队内部对"好人才"定义不一致、有人被叫"明星员工"但产出存疑。.
interview-mode
Use when simulating a technical interview to build confidence, expose reasoning gaps, and train structured communication under pressure.