agentmods.dev

audit-cursor

audit-cursor is a command for Claude Code from kelvinkosbab/AppBootstrapAI. It costs 0 tokens per session (295 once invoked), scanned A, a copy of audit-copilot, MIT.

A read-only command for checking one topic in a project against its AppBootstrapAI guidance. It loads only the files relevant to that topic and reports the findings without editing the project.

In plain words
What is it for?
Use it to audit topics such as architecture or concurrency in a code repository and receive a report in chat.
Why use it?
It limits the review to a chosen area, reducing unrelated context and preventing accidental changes.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

not rated 8repo today A scan 0 tokens copy · 89% MIT

Good fit Use it to audit topics such as architecture or concurrency in a code repository and receive a report in chat.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kelvinkosbab/appbootstrapai/audit-cursor
View source ↗ kelvinkosbab/AppBootstrapAI
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/kelvinkosbab/AppBootstrapAI

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.

agentmods badge for audit-cursor

README.md
[![agentmods](https://agentmods.dev/badge/commands/kelvinkosbab/appbootstrapai/audit-cursor/github.svg)](https://agentmods.dev/commands/kelvinkosbab/appbootstrapai/audit-cursor)
Your own site
<a href="https://agentmods.dev/commands/kelvinkosbab/appbootstrapai/audit-cursor"><img src="https://agentmods.dev/badge/commands/kelvinkosbab/appbootstrapai/audit-cursor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit-cursor

Your own site · 80×15
<a href="https://agentmods.dev/commands/kelvinkosbab/appbootstrapai/audit-cursor"><img src="https://agentmods.dev/badge/commands/kelvinkosbab/appbootstrapai/audit-cursor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 295 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 89% copy Near-identical to another mod 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 5.1 $0.00000 $0.00295
Opus 5.5 $0.00000 $0.00118
Sonnet 5.5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00030

Measured today against content hash f5a781e6a2f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-cursor 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 today.

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.

Origin

This is a copy

89% identical to audit-copilot — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

templates/commands/audit-cursor.md · 14 lines

What it actually says

AppBootstrapAI topic audit

Audit one area of this project with the AppBootstrapAI bundle, loading only that area's guidance.

  1. Find the bundle (the directory that holds install.sh), in this order:
    • $APPBOOTSTRAP_BUNDLE, if set.
    • bundle.path in .claude/.appbootstrap-manifest.json, if that directory still has install.sh.
    • Otherwise clone bundle.repo from the manifest (default https://github.com/kelvinkosbab/AppBootstrapAI) with git clone --depth 1 into a temp directory outside this repo.
  2. Pick the topic from the first word of the extra instructions. With no topic, list the topics in $BUNDLE/lib/topics.json (name and description) and stop.
  3. Run "$BUNDLE/install.sh" audit . --topic <topic> --json, then follow steps 3, 4 and 6 of playbooks/audit.md in the bundle. Read only the files in topic.rule_paths and topic.skill_paths, and only the skill references the review needs. Skip the steering review.
  4. This is read-only: report in chat, and don't edit, commit, or push unless I ask.

Any text after the command is the topic, then extra instructions (for example "concurrency" or "architecture only the Networking module").

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. today First seen · 14 lines · 0 tokens per session scan A f5a781e6a2f4

Subscribe to this mod's changes

audit-cursor is a command published in the GitHub repository kelvinkosbab/AppBootstrapAI (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 295 tokens. A static security scan graded it A with 0 findings. It is 89% identical to audit-copilot, differing in 5 lines, and is treated as a copy.

Code reviewaccessibilityai-rulesandroidiosjetpack-compose
Related

audit-cursor compared with commands from other repositories

audit-cursor next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
audit-cursorkelvinkosbab/AppBootstrapAICommand8todayMITA0Claude Code
feature-buildahmed3elshaer/everything-claude-code-mobileCommand664mo agoMITA45Claude Code
figma-applynaver/design-to-uiCommand82mo agoApache-2.0A31Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code