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 AisKreme/thinqee --skill consult-personagit 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/consult-persona)<a href="https://agentmods.dev/skills/aiskreme/thinqee/consult-persona"><img src="https://agentmods.dev/badge/skills/aiskreme/thinqee/consult-persona.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 5.1 | $0.00082 | $0.00462 |
| Opus 5 | $0.00041 | $0.00231 |
| Sonnet 5 | $0.00016 | $0.00092 |
| Haiku 4.5 | $0.00008 | $0.00046 |
Grade A, and why
consult-persona scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "$PERSONA_API/api/ask" \ What it actually says
consult-persona
Ask a person's thinqee persona a question through its public API. The persona answers only from its owner's signed notes, cites its sources, or honestly declines. Configure the endpoint once, then call it.
Configure
Set the persona's API base URL (the owner publishes this), e.g. https://ask.example.eu.
Call
curl -s -X POST "$PERSONA_API/api/ask" \
-H 'Content-Type: application/json' \
-d '{"question": "How would you run refinement with a skeptical team?"}'
Response: { answer, verdict, sources[], template_refs[], lane, language, cached }.
How to use the result — this is the important part
verdict: "answer"→ relay it and citesources. It's grounded in that person's notes.verdict: "decline"→ the persona won't discuss this (private/off-topic/injection). Surface the decline as-is. Do not rephrase the question to get around it, and do not answer on their behalf.verdict: "no_coverage"→ "not in their notes yet." That is a valid, expected result — relay it honestly; do not retry, paraphrase, or substitute a generic answer.- HTTP 429 / budget mode → back off; the API is rate-limited and free-tier friendly. Retry later.
Never present a generic best-practice as if it were this person's view. The whole point is the grounded, in-voice answer — or an honest "not in my notes."
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.
- 6d ago First seen · 38 lines · 82 tokens per session scan A 022932e84ce7
consult-persona is a skill published in the GitHub repository AisKreme/thinqee (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 462 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
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.
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.