Agent skill · Audited from source

Claude Smart

skill · ReflexioAI/claude-smartApache-2.0 licenceAudited 14 Oct 2026 · source a24aabf76e05

★ 783pushed today
!CAUTIONGrade B · 89/100 · 2 findings · a24aabf
783repo stars · whole ReflexioAI/claude-smart

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit a24aabf76e05 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 2 findings, 0 critical or high. What it does: Codex-only — use when the user asks to run claude-smart commands in Codex, including claude-smart show, learn, restart, dashboard, clear-all, or slash-like requests such as /claude-smart:learn. In Claude Code the native…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Claude Smart (ReflexioAI/claude-smart)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/reflexioai/claude-smart

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high2 medium0 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN2
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

Audit 0.4.1 · source sha a24aabf76e05 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherReflexioAI GitHub organizationOwner of the repository this skill is read from
  • Source folderReflexioAI/claude-smart/plugin/skills/claude-smartThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdicta24aabf76e05A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Codex-only — use when the user asks to run claude-smart commands in Codex, including claude-smart show, learn, restart, dashboard, clear-all, or slash-like requests such as /claude-smart:learn. In Claude Code the native…

---
name: claude-smart
description: Codex-only — use when the user asks to run claude-smart commands in Codex, including claude-smart show, learn, restart, dashboard, clear-all, or slash-like requests such as /claude-smart:learn. In Claude Code the native plugin slash commands handle these; do not invoke this skill there.
---

# claude-smart Commands In Codex

Codex does not currently support plugin-provided slash commands. When the user
asks for a claude-smart command, run the equivalent shell command through the
active plugin root. This skill is Codex-specific; under Claude Code the native
`/claude-smart:*` slash commands already exist, so do not fall back to the
shell commands there.

## Command Map

- Dashboard: `bash ~/.reflexio/plugin-root/scripts/dashboard-open.sh`
- Show learned state: `bash ~/.reflexio/plugin-root/scripts/cli.sh show`
- Learn from the latest turn: `bash ~/.reflexio/plugin-root/scripts/cli.sh learn`
- Learn with a note: `bash ~/.reflexio/plugin-root/scripts/cli.sh learn --note "<note>"`
- Restart backend/dashboard: `bash ~/.reflexio/plugin-root/scripts/cli.sh restart`
- Clear all learned state: `bash ~/.reflexio/plugin-root/scripts/cli.sh clear-all --yes`

## Behavior

1. Treat slash-like prompts such as `/claude-smart:show` as requests to run the
   matching shell command above.
2. For `learn`, preserve any user-provided note exactly as the note text.
3. For `clear-all`, require explicit confirmation before running it because it
   deletes all reflexio interactions, preferences, and skills.
4. If `~/.reflexio/plugin-root` is missing or broken, rerun
   `npx claude-smart install --host codex` to repair installation, then tell the
   user to start a new Codex session and rerun the command.
5. After running a command, summarize the important output concisely.

Excerpt, first 1,812 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit a24aabf

Download folder ↗
git clone https://github.com/ReflexioAI/claude-smart
git -C claude-smart checkout a24aabf76e05

The author documents no install command, so this uses the repository directly. Our verdict covers commit a24aabf76e05 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source a24aabf76e05

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/reflexioai/claude-smart/badge.svg)](https://modelsatlas.com/skills/reflexioai/claude-smart/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/reflexioai/claude-smart/badge.svg)](https://modelsatlas.com/skills/reflexioai/claude-smart/)

Questions about Claude Smart

What does the Claude Smart skill do?
Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
Is Claude Smart safe to install?
With care. The audit graded it B (89/100) and found 2 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Claude Smart access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Claude Smart work with?
Its documentation mentions claude-code and codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (a24aabf76e05), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.