review-drift

review-drift is a command for Claude Code from jubayertalha/vibeframe. It costs 18 tokens per session (286 once invoked), scanned A, original, MIT.

A command for reviewing VibeFrame drift findings, which are detected differences between the project model and its code.

In plain words
What is it for?
Examining each finding, fixing code or updating the model, repairing links, assigning files, and validating the result.
Why use it?
It helps resolve cases where planned steps are missing, code violates recorded constraints, links point to the wrong symbols, or files are not assigned to components.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vibeframe plugin — 1 skill, 3 commands, 4 hooks, 1 MCP server shipped together

Good fit Examining each finding, fixing code or updating the model, repairing links, assigning files, and validating the result.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jubayertalha/vibeframe/review-drift
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/jubayertalha/vibeframe

Made for: Claude Code.

Or install vibeframe, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 4 hooks, 1 MCP server.

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 review-drift

README.md
[![agentmods](https://agentmods.dev/badge/commands/jubayertalha/vibeframe/review-drift/github.svg)](https://agentmods.dev/commands/jubayertalha/vibeframe/review-drift)
Your own site
<a href="https://agentmods.dev/commands/jubayertalha/vibeframe/review-drift"><img src="https://agentmods.dev/badge/commands/jubayertalha/vibeframe/review-drift/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 review-drift

Your own site · 80×15
<a href="https://agentmods.dev/commands/jubayertalha/vibeframe/review-drift"><img src="https://agentmods.dev/badge/commands/jubayertalha/vibeframe/review-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 286 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00286
Opus 5 $0.00009 $0.00143
Sonnet 5 $0.00004 $0.00057
Haiku 4.5 $0.00002 $0.00029

Measured 8d ago against content hash 4fb07081ca90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-drift 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 8d 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.

plugin/commands/review-drift.md · 22 lines

What it actually says

Review and resolve open VibeFrame drift findings.

  1. vibe_query kind=drift — open findings with evidence, most recent first.
  2. For each finding, examine the evidence (files and lines are exact — the validator is deterministic and does not guess):
    • divergence / constraint-violation: decide whether the code or the declared design is right. Fix the code, or declare the dependency/constraint change (and vibe_decide why) so the model matches reality.
    • absence: implement the missing step, or remove/adjust the declared step if it was over-planned.
    • broken-binding: re-link with vibe_link using the candidates in the evidence.
    • orphan: assign the file to a component (vibe_link component=<id> file=<glob>) or leave it and recommend dismissal if it is genuinely outside the architecture.
  3. After changes, vibe_validate to confirm findings close (they auto-resolve when no longer detected).
  4. Report anything that needs a human verdict (accept-as-new-intent or dismiss) with your recommendation — those verbs belong to the human in the browser UI.
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. 8d ago First seen · 22 lines · 18 tokens per session scan A 4fb07081ca90

Subscribe to this mod's changes

review-drift is a command published in the GitHub repository jubayertalha/vibeframe (0 stars, last pushed 11d ago), licensed MIT. It adds 18 tokens to every session and 286 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.