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 PacificStudio/openase --skill deep-interviewgit clone --depth 1 https://github.com/PacificStudio/openaseWrote 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/pacificstudio/openase/deep-interview)<a href="https://agentmods.dev/skills/pacificstudio/openase/deep-interview"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/deep-interview/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/pacificstudio/openase/deep-interview"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/deep-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 40 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 52 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00021 | $0.00727 |
| Opus 5.5 | $0.00008 | $0.00291 |
| Sonnet 5.5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
deep-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 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Interview
Overview
Use this skill when the request is broad, ambiguous, or missing concrete acceptance criteria. Its job is to turn a vague idea into an execution-ready requirement brief before deeper planning or implementation begins.
When To Use
- The user wants to explore a broad idea without making hidden assumptions.
- The request lacks clear scope, non-goals, or success criteria.
- A later planning or execution step would otherwise guess at intent.
- The change touches an existing codebase and the current pattern or boundary is still unclear.
Do Not Use
- The request already names concrete files, symbols, errors, or acceptance criteria.
- The user explicitly wants to skip clarification and accept the risk.
- A complete requirement brief or implementation plan already exists.
Workflow
-
Start with context you can gather yourself.
- Inspect the codebase, docs, or surrounding ticket context before asking the user about project internals.
- Summarize what is already known and which parts are still assumptions.
-
Ask one question at a time.
- Do not batch multiple unrelated questions.
- Ask the highest-leverage unresolved question first.
-
Prioritize requirement clarity in this order.
- Intent: why the user wants the change.
- Outcome: what end state should exist when the work is done.
- Scope: how far the change should go.
- Non-goals: what should stay out of scope.
- Decision boundaries: what the agent may decide without asking again.
- Constraints: technical, business, operational, or timeline limits.
- Success criteria: how completion will be judged.
-
Pressure-test each important answer.
- Ask for an example, counterexample, or concrete signal.
- Surface the hidden assumption behind the answer.
- Force a boundary or tradeoff when the scope is still fuzzy.
- If the user is describing symptoms, steer back toward the underlying problem.
-
Keep the interview efficient.
- Prefer evidence-backed confirmation questions for brownfield work.
- Do not ask the user for facts you can inspect directly.
- Stop once the request is clear enough to plan, not after exhausting every possible question.
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 · 89 lines · 21 tokens per session scan A e160e94ca68f
deep-interview is a skill published in the GitHub repository PacificStudio/openase (269 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 727 once invoked, about $0.0001 per session on Opus 5.5. 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
aisee:init
A project setup and audit helper for OpenSpec, a system for planning and tracking software changes, in Aisee projects.
aisee:srs
A structured conversation and documentation tool for creating a software requirements specification, or SRS. An SRS records users, goals, scope, workflows, rules, permissions, exceptions, and acceptance needs before technical design or coding.
aisee:change-author
A document-writing tool for one already-approved OpenSpec change. OpenSpec is a way to describe software changes in structured documents before implementation.
aisee:change-plan
A planning tool that turns an approved software request or project fact into one or more clearly separated OpenSpec changes. OpenSpec is a structured way to plan and describe software work before implementation.
aisee:image-object
A workflow for extracting reusable objects from an existing image, such as a product or person, and saving cutouts, masks, repaired backgrounds, and image variants. A mask is a shape that marks which pixels belong to the selected object.
aisee:reflect
A guide for reviewing a work session and saving reusable lessons as project documents. It distinguishes temporary suggestions from confirmed long-term team knowledge and from records of specific solved problems.