A read-only scanner for Flutter code, a toolkit for building apps with Dart, that reports visual, layout, platform, and code-quality problems.

Auditing Dart files, checking screens before visual cleanup, and reviewing new features for common Flutter mistakes.

It finds likely issues before they cause regressions and gives each problem a severity and suggested fix without changing files.

audit — Command for Claude Code by obiwancenobi

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.

Clone the repo

git clone --depth 1 https://github.com/obiwancenobi/klamben

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/obiwancenobi/klamben/audit.svg)](https://agentmods.dev/commands/obiwancenobi/klamben/audit)

Your own site

<a href="https://agentmods.dev/commands/obiwancenobi/klamben/audit"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/audit.svg" alt="Measured on agentmods" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 482 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00482
Opus 5	$0.00012	$0.00241
Sonnet 5	$0.00005	$0.00096
Haiku 4.5	$0.00002	$0.00048

Measured 6d ago against content hash 866bdd8e6d18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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.

src/commands/audit.md · 60 lines

What it actually says

/audit

Scan Flutter code for anti-patterns. Read-only — never modifies files.

When to use

User asks "check this file" / "audit my code" / "what's wrong here"
Before running /polish or /normalize to see the full issue list
After adding a feature, to verify it doesn't introduce regressions

Process

Check design context: If .klamben.md exists in the project root, read it first. Apply the project's brand, platform targets, accessibility tier, and existing patterns to your work below.
Load the full rule catalog from src/rules/rules.json (or equivalent in the installed project)
For the target path (default: current file or lib/), walk every .dart file
For each rule, check matching AST patterns
Produce a ranked issue list grouped by severity (error > warning > info)
Do not modify any file. Report only.

Output format

Audit for lib/screens/home.dart

ERROR (1)
  24:7  layout/missing-safearea  Scaffold body without SafeArea
        → Wrap body in SafeArea(child: ...)

WARNING (2)
  11:15 visual/hardcoded-color  Container uses Colors.purple
        → Use Theme.of(context).colorScheme.primary
  47:3  visual/nested-cards     Card inside Card
        → Collapse to a single Card with ListTile children

INFO (1)
  3:7   code-quality/missing-const  Text widget can be const
        → Add const

4 issues (1 error, 2 warnings, 1 info) in 1 file.

After audit

Suggest next step based on severity mix:

Errors present → run /harden or fix manually, then re-audit
Warnings only → run /polish or /normalize
Info only → optional cleanup via /polish

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.

6d ago First seen · 60 lines · 24 tokens per session scan A 866bdd8e6d18

Subscribe to this mod's changes

audit is a command published in the GitHub repository obiwancenobi/klamben (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 482 once invoked, about $0.0001 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.

Debugging agent-skills ai ai-harness design-skills flutter slash-command

audit

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/audit

When to use

Process

Output format

After audit

What this file has done since we first saw it

Other commands, from other repositories

isdown

dev-fix

verify-bug

codebase-review

inconsistences

run-agents-for-issues