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/mifunedev/openharness/interviewnpx skills add mifunedev/openharness --skill interviewgit clone --depth 1 https://github.com/mifunedev/openharnessWhat 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 | $0.00073 | $0.02265 |
| Opus 5 | $0.00036 | $0.01132 |
| Sonnet 5 | $0.00015 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade C, and why
interview scanned grade C 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 2d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Do not refuse silently. The skip is a signal, not an absence. How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview
Resolve scope ambiguity before non-trivial work by batching 2–4 task-specific multiple-choice questions through AskUserQuestion, then proceeding with a short scope brief that reflects the answers.
When to use
/interviewinvoked explicitly (with or without a task description).- Proactively, before non-trivial work where scope, intent, or constraints are ambiguous AND the user hasn't already specified them in the prompt.
The structured tool (AskUserQuestion) earns its keep when the user can resolve scope in one click rather than a paragraph of free-text Q&A.
When NOT to use
Skip — and announce the skip — when any of these hold:
- Trivial edits — single-file typo, comment-only edit, format/whitespace pass.
- Already specified — the user's prompt already names goal + scope + constraints + acceptance criteria.
- Follow-up turn — same task, context already established earlier in the conversation.
- Trivial CLI invocations —
/release,/ci-status,gh pr list, etc. - Plan approval moments — that's
ExitPlanMode, not this skill.AskUserQuestionis for picking among options, not approving a finished plan. - About to run
/prdor/spec plan— those have their own clarifier. For v1 the user chooses one or the other; do not stack.
Instructions
1. Classify trivial vs non-trivial
If the task is trivial (per § When NOT to use), announce the skip and continue:
Skipping interview — this looks trivial. Proceeding directly.
Do not refuse silently. The skip is a signal, not an absence.
2. Extract what's already known
Read the conversation context. List, internally, what's already specified — goal, files touched, mode, constraints, acceptance. Do not re-ask anything the context already answers. A question whose answer is already in the prompt is a tell that the model didn't read.
3. Pick 2–4 questions
Each question must clear the bar in § Question quality bar below. If you can't write 2 that clear the bar, ask 1 (sequential calls are fine) or skip and announce why. Don't quota-fill to reach 4.
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.
- 2d ago First seen · 199 lines · 73 tokens per session scan C 2bf03647e9bf
interview is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,265 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
social-media
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.