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/aiskreme/thinqee/persona-interviewnpx skills add AisKreme/thinqee --skill persona-interviewgit clone --depth 1 https://github.com/AisKreme/thinqeeWrote 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/aiskreme/thinqee/persona-interview)<a href="https://agentmods.dev/skills/aiskreme/thinqee/persona-interview"><img src="https://agentmods.dev/badge/skills/aiskreme/thinqee/persona-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 | $0.00081 | $0.00526 |
| Opus 5 | $0.00041 | $0.00263 |
| Sonnet 5 | $0.00016 | $0.00105 |
| Haiku 4.5 | $0.00008 | $0.00053 |
Grade A, and why
persona-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 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.
What it actually says
persona-interview
You help the user build their own thinqee persona by running the engine's interviewer. You are a facilitator, not a ghostwriter — never invent the user's answers or values. The premise is "no sentence I haven't signed."
Prerequisite
The thinqee CLI is installed with the agents extra and a persona workspace exists:
pip install "thinqee[agents]"
thinqee init ./my-persona # if they don't have one yet
What to do
- Ask the user which session they want (or which declined question to work on):
Avoice & how they think ·Bvalues (from real stories) ·Cguardrails ·Dlogistics ·Ea craft method ·Fa contested position ·Gtemplates & sources.
- Run the CLI and let it drive the questions — do not freelance the interview:
thinqee interview --session <A-G> --kb ./my-persona/knowledge # or, for one declined question: thinqee interview --gap "<the question>" --kb ./my-persona/knowledge - Relay each question to the user one at a time. Push for a concrete story, not adjectives; force a pick on false "it depends"; ask where they differ from the textbook. Pass their raw answers straight through.
- The CLI drafts an unsigned note (
signed: false). Remind the user to read it line by line, setsigned: trueonly for sentences they'd defend, and commit it. There is no build step —thinqee askvalidates the knowledge base itself and will refuse to run on an unsigned note.
Never
- Never set
signed: truefor the user or write a value/opinion they didn't state. - Never summarize their personality back at them mid-interview.
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 · 43 lines · 81 tokens per session scan A d3dbf33e8d88
persona-interview is a skill published in the GitHub repository AisKreme/thinqee (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 526 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
data-analysis
Comprehensive data analysis skill for CSV files using Python and pandas.
diagram-design
Best practices for creating research diagrams with Excalidraw MCP tools.
debug-evals
Debug haiku.rag evaluation runs in Logfire. Use when asked to look at Logfire for an eval run, find failing or low-scoring eval cases, compare runs, check citation quality (citedmap) or judge pass rate (answerequivalent), or explain why an eval case failed. Drives the Logfire MCP against the evals service, or the…
data-formats
Working with diverse data formats: binary, text, structured, and custom.
systematic-debugging
Systematic approach to diagnosing and fixing errors.
verification-strategy
Thorough verification of completed work before declaring done.