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/imaginenpx skills add mifunedev/openharness --skill imaginegit clone --depth 1 https://github.com/mifunedev/openharnessWrote 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/mifunedev/openharness/imagine)<a href="https://agentmods.dev/skills/mifunedev/openharness/imagine"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/imagine.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 | $0.00161 | $0.01595 |
| Opus 5 | $0.00081 | $0.00797 |
| Sonnet 5 | $0.00032 | $0.00319 |
| Haiku 4.5 | $0.00016 | $0.00160 |
Grade A, and why
imagine 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 yesterday.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Imagine
One-shot generator that turns a fuzzy scenario into a draft PRD sketch under .claude/specs/<slug>/spec.md. The output is scratch-input for /spec plan — gitignored by default, never committed, designed to be edited locally and then passed via /spec plan --plan <path> to the formalization pipeline.
When to use
- The user has an idea but the shape is still fuzzy — they don't want to sit through
/prd's 3–5 lettered Q&A yet. - The user wants a tangible artifact they can edit before formalizing.
- Quick what-if exploration: "imagine a /summarize command", "what if we added X".
When NOT to use
/prd— when the feature is already well-defined and ready for a structured PRD with numbered FRs and acceptance criteria./imagineoutputs a sketch, not a PRD./spec— when ready for the full pipeline (PRD → task folder → issue → branch → draft PR → build)./imagineproduces input for/spec plan; it does not replace it./interview— when the goal is to narrow scope on a known task./imagineis for generating a new task shape from a scenario.
The job
- Receive
<scenario>as a free-text argument. - Derive a slug from the scenario.
- One-shot generate the spec body (no clarifying questions).
- Write
.claude/specs/<slug>/spec.md. - Print the path and the next-step command.
- Append a Memory Protocol entry.
Step 1 — Parse <scenario> and derive slug
Arguments received: $ARGUMENTS
The slug rule is the same one /prd uses (see .claude/skills/prd/SKILL.md § Output → Feature name). Do not invent a new rule.
- Lowercase, kebab-case, charset
[a-z0-9-]+, ≤5 words, must not equalarchive. - Derive the slug from the scenario by extracting the salient noun phrase (the thing being imagined), not by truncating the full scenario.
imagine a slack /summarize command that condenses the last N messages→slack-summarize-commandimagine a dry-run mode for /release→release-dry-run-mode
- If the derived slug is empty, exceeds 5 words, contains
/, or equalsarchive, reject and ask the user for an explicit short name.
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.
- yesterday Changed 96d09a921656
- 5d ago First seen · 141 lines · 161 tokens per session scan A 316707b7d1f6
imagine is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed today), licensed Apache-2.0. It adds 161 tokens to every session and 1,595 once invoked, about $0.0008 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 2026-08-30.
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.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
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…