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/dragoon0x/usemindit/mindit-auditnpx skills add Dragoon0x/usemindit --skill mindit-auditgit clone --depth 1 https://github.com/Dragoon0x/useminditWrote 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/dragoon0x/usemindit/mindit-audit)<a href="https://agentmods.dev/skills/dragoon0x/usemindit/mindit-audit"><img src="https://agentmods.dev/badge/skills/dragoon0x/usemindit/mindit-audit.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 | $0.00122 | $0.01309 |
| Opus 5 | $0.00061 | $0.00655 |
| Sonnet 5 | $0.00024 | $0.00262 |
| Haiku 4.5 | $0.00012 | $0.00131 |
Grade A, and why
mindit-audit 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mindit-audit
The first of three meta skills. Run this when the user wants a full review, not a single force.
What this skill does
Runs all eight forces against the same subject and produces a scorecard. Surfaces the lowest-scoring force as the bottleneck to address first. Inspired by the observation that uneven force profiles indicate uneven attention: a design scoring 90 on Clarity and 20 on Correctability has not been thought through, it has been polished.
When to run this
- The user asks for "a review," "full audit," "complete review," "review my design."
- The user has just shown a design and asked an open-ended question like "what do you think" or "what should I change."
- The user is new to mindit and does not yet know which force applies.
- The user wants a launch readiness check before shipping a feature.
How to analyze
-
Capture the subject and the constraints. Same as for any single-force skill: what is being analyzed, what hard limits apply, what audience, what platform. If essential information is missing, ask once before running.
-
Run each force in turn. Follow the procedure in each force's own SKILL.md. Do not shortcut. Eight artifacts get produced, plus a synthesis.
mindit-claritymindit-continuitymindit-constraintmindit-consequencemindit-contextmindit-costmindit-confidencemindit-correctability
-
Identify the bottleneck. Find the lowest-scoring force. That is where the design is weakest, and where attention will produce the largest improvement.
-
Identify the lopsidedness. Look at the spread between the highest and the lowest force. A wide spread (e.g. 90 down to 25) usually means the team is over-investing in some forces and ignoring others.
-
Write the synthesis artifact. See "Output format."
Rubric
The audit does not have its own rubric; it inherits the rubrics of the eight force skills. The audit's own score is reported as the lowest force score (the bottleneck), not an average. Averages mask the failure mode: a 70 average with a 25 in Correctability is still going to fail at launch.
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 · 128 lines · 122 tokens per session scan A ac767039c955
mindit-audit is a skill published in the GitHub repository Dragoon0x/usemindit (2 stars, last pushed 3mo ago), licensed MIT. It adds 122 tokens to every session and 1,309 once invoked, about $0.0006 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
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.