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 pantheon-org/tekhne --skill guided-interviewgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/guided-interview)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/guided-interview"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/guided-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/pantheon-org/tekhne/guided-interview"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/guided-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00108 | $0.02352 |
| Opus 5.5 | $0.00043 | $0.00941 |
| Sonnet 5.5 | $0.00022 | $0.00470 |
| Haiku 4.5 | $0.00011 | $0.00235 |
Grade A, and why
guided-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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guided Interview — One Question, Concrete Options, Adaptive
Interviews fail two ways: dumping a wall of questions on the user at once, or asking open questions that make the user do the work of drafting an answer from scratch. This skill fixes both — ask one question, make each option a genuine, distinct answer the user can just pick, and let every answer reshape what gets asked next.
Mindset
Every question should be answerable in one short reply, not a paragraph. The interview is not a checklist to complete — it is a chain of decisions where each answer changes the shape of the next question. Treat "I don't know" or "other" as real signal, not a failure to plan for.
Prerequisites
Applicable only when ALL of the following hold:
- The user asked to be interviewed, walked through a decision, or to "help me figure out" a specific, nameable topic.
- The topic has enough shape to generate concrete, meaningfully different options — not "tell me about your life" or anything too diffuse to enumerate.
- Interrupting the current task to interview is not worse than proceeding directly (the user isn't mid-emergency or explicitly time-constrained).
If any prerequisite is absent, skip this skill. For open-ended ambiguity where the problem itself
is unclear, use socratic-method instead — that skill probes assumptions with open questions;
this one narrows a known topic down to a decision via concrete choices.
When to use
BY DEFAULT, reach for this skill whenever a topic has a real, enumerable decision space. PREFER a direct answer instead when the ask is mechanical or the user is visibly time-constrained. TYPICALLY, the whole interview resolves in 3-6 questions — consider that a rough budget, not a hard cap.
- The user explicitly asks to be interviewed, "asked one question at a time", or offered options
- Requirements gathering for a plan, ticket, design doc, or brief where several discrete decisions must be made before work can start
- Exploring a decision space where the user has unstated preferences that surface faster through concrete choices than through open questions
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .audits/2026-10-02/Analysis.md 487 B
- .audits/2026-10-02/audit.json 549 B
- .audits/2026-10-02/Remediation.md 1.4 KB
- evals/instructions.json 3.5 KB
- evals/scenario-01/capability.txt 131 B
- evals/scenario-01/criteria.json 1.7 KB
- evals/scenario-01/task.md 1.7 KB
- evals/scenario-02/capability.txt 145 B
- evals/scenario-02/criteria.json 1.2 KB
- evals/scenario-02/task.md 1.2 KB
- evals/scenario-03/capability.txt 150 B
- evals/scenario-03/criteria.json 1.3 KB
- evals/scenario-03/task.md 1.5 KB
- evals/scenario-04/capability.txt 151 B
- evals/scenario-04/criteria.json 1.3 KB
- evals/scenario-04/task.md 1.7 KB
- evals/summary.json 638 B
- references/question-design.md 2.3 KB
- references/worked-example.md 2.3 KB
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 · 200 lines · 108 tokens per session scan A f5a6f1ea813c
guided-interview is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 2,352 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
vite
Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.