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.
git clone --depth 1 https://github.com/kok-o/koko-contextos-agentsWrote 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/kok-o/koko-contextos-agents/interview-me)<a href="https://agentmods.dev/rules/kok-o/koko-contextos-agents/interview-me"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/interview-me/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/kok-o/koko-contextos-agents/interview-me"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/interview-me.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 | $0.00033 | $0.00775 |
| Opus 5 | $0.00016 | $0.00387 |
| Sonnet 5 | $0.00007 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
interview-me 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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: interview-me
interview-me
Overview
Structured requirements interrogation framework inspired by addyosmani/agent-skills. Prevents wasted cycles by transforming vague user intents into crisp, unambiguous architectural constraints through single-question progressive interview loops.
When to Use
Activate whenever:
- User task has underspecified requirements, open UX decisions, or multiple viable architectural trade-offs.
- A high-blast-radius change (database migrations, auth refactor, API contract change) is requested.
- Explicitly triggered via
/spec,/interview, or "ask me questions first".
Rules & Patterns
1. The One-Question-At-A-Time Rule
Never overwhelm the user with a 10-point interrogation form.
- Ask exactly ONE focused question per turn (or at most two tightly-coupled binary options).
- Provide the recommended option first with clear rationale:
"(Recommended) Option A because...". - Always allow write-in or clarification.
2. The 4 Interrogation Dimensions
Interrogate in this strict priority order:
- Business Outcome & Invariants:
- What core problem does this solve?
- What behavior is strictly forbidden?
- Scope Boundaries (In vs Out):
- What must be delivered in this atomic slice?
- What is explicitly deferred to later?
- Technical Constraints:
- Versions, libraries, database engines, backwards compatibility requirements.
- Edge Cases & Failure Modes:
- What happens on network disconnect, empty response, or unauthorized token?
3. Progressive Synthesis
After each user answer:
- Acknowledge the decision and update the mental model.
- If more critical decisions remain, ask the next question.
- Once 2–4 key questions are resolved, synthesize the formal Feature Spec and transition to
engineering-workflow([PHASE: Plan]).
Code Examples
Interactive Interview Turn Example
**Question 1 of 3 (Authentication Strategy)**
Before implementing the API authentication layer, we need to align on session storage:
1. **(Recommended) HTTP-only Secure Cookies with Refresh Tokens**:
- *Why*: Immune to XSS token theft, standard for web dashboards.
2. **Bearer Token in Authorization Header**:
- *Why*: Ideal if this API will also be consumed by mobile apps or third-party CLI tools.
Which model fits your architecture best?
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.
- 4d ago First seen · 100 lines · 33 tokens per session scan A 7729a83ec9db
interview-me is a cursor rule published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 5d ago), licensed MIT. It adds 33 tokens to every session and 775 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 2026-09-05.
Other cursor rules, from other repositories
deepen-architecture
Find deepening opportunities in a codebase, informed by the domain language in specs/tech-architecture/tech-stack.md and the decisions in specs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
craft-skill
Create new bigpowers skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill for the bigpowers lifecycle.
grill-me
Interactive assumption-surfacing Q&A that stress-tests a plan through relentless questioning until every decision is resolved. Use when user wants to challenge a plan, validate decisions from conversation/context, or mentions "grill me". For doc-grounded variant, use grill-with-docs.
run-planning
DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (specs/planning-status.yaml) through survey-context → scope-work → research-first → elaborate-spec → plan-release → slice-tasks. NOT a duplicate of plan-work or the planning spine; it orchestrates the pre-coding discover phase only.
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
terse-mode
Fallback ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use ONLY when context is critically long and compressing output is necessary to continue. Not a strategy — token discipline comes from code shape (small functions…