Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Zchary1106/agent-interview-hubnpx agentmods add rules/zchary1106/agent-interview-hub/interview-collectorWrote 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/rules/zchary1106/agent-interview-hub/interview-collector)<a href="https://agentmods.dev/rules/zchary1106/agent-interview-hub/interview-collector"><img src="https://agentmods.dev/badge/rules/zchary1106/agent-interview-hub/interview-collector/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/rules/zchary1106/agent-interview-hub/interview-collector"><img src="https://agentmods.dev/badge/rules/zchary1106/agent-interview-hub/interview-collector.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 | $0.00022 | $0.00301 |
| Opus 5.5 | $0.00009 | $0.00120 |
| Sonnet 5.5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
interview-collector scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://r.jina.ai/https://example.com/page" What it actually says
Interview Collector Agent
When working on interview collection:
- Search public sources only.
- Do not bypass login walls, paywalls, or anti-bot controls.
- Do not request or commit cookies, tokens, or credentials.
- Summarize sources; do not copy long external content.
- Keep
data/interviews.jsonas the structured source of truth. - Generate Markdown summaries from structured data.
- Avoid unstable Xiaohongshu direct links in public docs; keep
source_note_idandsource_lookup.
Recommended commands:
python3 scripts/collect_interviews.py doctor
python3 scripts/collect_interviews.py search --query "AI Agent 大模型 面经 2026"
agent-reach doctor --json
mcporter call 'exa.web_search_exa(query: "site:nowcoder.com AI Agent 大模型 面经 2026", numResults: 10)'
curl -s "https://r.jina.ai/https://example.com/page"
opencli xiaohongshu search "AI Agent 面经" -f yaml --window background
gh search repos "AI Agent interview" --limit 10 --json fullName,description,stargazersCount,url,updatedAt
python3 -m json.tool data/interviews.json
python3 scripts/build_site.py
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.
- 1mo ago First seen · 31 lines · 22 tokens per session scan A de41f787bffc
interview-collector is a cursor rule published in the GitHub repository Zchary1106/agent-interview-hub (837 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 301 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
context-loader
Use when starting a new substantive conversation or switching contexts — load relevant memories to prime the session with continuity.
memory-informed-longitudinal-work
Long-running multi-session work (research, eval loops, iterative benchmarks) — resume prior lessons, capture per-run outcomes, build up stable truths over time.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
memory-informed-design
Use when making architecture, API, or design decisions — consult prior decisions and capture new ones in-flight.
memory-informed-refactor
Use before substantive refactors — load relevant prior context, capture refactor insights as they land.
entity-detection
Pensyve entity detection — canonicalization and fallback rules for recall scoping.