mindit-audit

mindit-audit is a skill for Claude Code, Codex from Dragoon0x/usemindit. It costs 122 tokens per session (1,309 once invoked), scanned A, original, MIT.

A complete design review that checks eight areas: clarity, continuity, constraints, consequences, context, cost, confidence, and ease of correction. It produces a scorecard and identifies the weakest area.

In plain words
What is it for?
Use it for a full design audit, an open-ended design review, or a readiness check before launching a feature.
Why use it?
It reveals problems that a review focused on only one aspect might miss, and helps decide what to fix first.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/dragoon0x/usemindit/mindit-audit
Any agent
npx skills add Dragoon0x/usemindit --skill mindit-audit
Clone the repo
git clone --depth 1 https://github.com/Dragoon0x/usemindit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mindit-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/dragoon0x/usemindit/mindit-audit.svg)](https://agentmods.dev/skills/dragoon0x/usemindit/mindit-audit)
Your own site
<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>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,309 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash ac767039c955, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/mindit-audit/SKILL.md · 128 lines

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

  1. 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.

  2. 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-clarity
    • mindit-continuity
    • mindit-constraint
    • mindit-consequence
    • mindit-context
    • mindit-cost
    • mindit-confidence
    • mindit-correctability
  3. Identify the bottleneck. Find the lowest-scoring force. That is where the design is weakest, and where attention will produce the largest improvement.

  4. 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.

  5. 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.

Read the full file on GitHub · 128 lines

Changes

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.

  1. 4d ago First seen · 128 lines · 122 tokens per session scan A ac767039c955

Subscribe to this mod's changes

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.