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 skills add shawnpang/startup-founder-skills --skill interview-kitgit clone --depth 1 https://github.com/shawnpang/startup-founder-skillsWrote 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/shawnpang/startup-founder-skills/interview-kit)<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/interview-kit"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/interview-kit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/interview-kit"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/interview-kit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.01751 |
| Opus 5 | $0.00017 | $0.00875 |
| Sonnet 5 | $0.00007 | $0.00350 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade A, and why
interview-kit 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- interview-kit — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Kit
When to Use
- Designing a structured interview loop for a specific role and level
- Creating standardized question banks organized by interview round type
- Building scoring rubrics for consistent candidate evaluation across interviewers
- Reducing interviewer bias with process controls and calibration
- Turning a job description into a repeatable evaluation process
- Calibrating interview panels after quarterly hiring outcome reviews
Context Required
- From startup-context: Company stage, team size, engineering culture, current interview process (if any), hiring velocity
- From user: Role title, level (junior/mid/senior/staff), key competencies to evaluate, number of interview rounds the team can support, whether a take-home or live exercise is preferred
Workflow
- Define competencies — Extract 4-6 core competencies from the job description. Split into technical skills, domain knowledge, collaboration traits, and startup-fit signals. Each competency must be evaluable with observable evidence.
- Design the interview loop — Map competencies to interview stages with explicit, non-overlapping objectives per round. Typical startup loop: recruiter/founder screen, technical assessment, team interview, values interview. Assign timing and interviewers to each stage.
- Write structured questions — For each stage, write 3-5 primary questions with follow-up probes. Every question must map to a specific competency. Include "what good looks like" answer guidance so interviewers know what signal they are looking for.
- Build scorecards — Create a 1-4 rating scale (not 1-5 — it creates a "3 means fine" dead zone). Define behavioral anchors at each level specific to the role. Interviewers must score independently before the debrief.
- Design take-home or live exercise — If applicable, create a practical assessment that mirrors real work. Time-cap it (2-4 hours max), share the evaluation rubric with the candidate upfront, and always follow up with a live walkthrough.
- Add anti-bias guardrails — Require structured debrief instructions, independent scoring protocol, and a checklist of common bias traps. Every candidate for the same role gets the same core questions in the same order.
- Plan calibration cadence — Set quarterly recalibration using hiring outcome data. Review whether loop design still surfaces the right signals based on quality-of-hire metrics.
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.
- 11d ago First seen · 142 lines · 34 tokens per session scan A d838727f6f05
interview-kit is a skill published in the GitHub repository shawnpang/startup-founder-skills (320 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,751 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…