corrections

corrections is a plugin for Claude Code from melodic-software/claude-code-plugins. Its manifest loads nothing; the 1 skill it bundles cost 91 tokens per session together, scanned A, original, MIT.

A check-making plugin that turns a recurring code correction into a testable rule. Its proof script runs the check against the old and current versions in temporary Git worktrees, which are separate working directories for different revisions.

In plain words
What is it for?
Use it when converting repeated review findings or bug fixes into enforced checks across code revisions.
Why use it?
It helps show that a proposed check catches the old problem and accepts the corrected code, rather than merely passing by accident.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit Use it when converting repeated review findings or bug fixes into enforced checks across code revisions.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add melodic-software/claude-code-plugins
/plugin install corrections
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/melodic-software/claude-code-plugins

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 corrections

README.md
[![agentmods](https://agentmods.dev/badge/plugins/melodic-software/claude-code-plugins/corrections/github.svg)](https://agentmods.dev/plugins/melodic-software/claude-code-plugins/corrections)
Your own site
<a href="https://agentmods.dev/plugins/melodic-software/claude-code-plugins/corrections"><img src="https://agentmods.dev/badge/plugins/melodic-software/claude-code-plugins/corrections/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 corrections

Your own site · 80×15
<a href="https://agentmods.dev/plugins/melodic-software/claude-code-plugins/corrections"><img src="https://agentmods.dev/badge/plugins/melodic-software/claude-code-plugins/corrections.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 91 tokens a session between them.
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.
Security

Grade A, and why

corrections 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.

plugins/corrections/.claude-plugin/plugin.json · 32 lines

What it actually says

{
  "name": "corrections",
  "version": "0.7.0",
  "description": "Turns a recurring correction into an enforced check. /corrections:codify counts how often a described mistake recurs, picks the strongest enforcement-ladder rung that can catch it, and proposes a check proven to fail on the old code and pass on the current code, using scripts/prove-check.sh to run it in temporary worktrees at two refs.",
  "author": {
    "name": "Melodic Software",
    "email": "[email protected]"
  },
  "license": "MIT",
  "keywords": [
    "corrections",
    "codify",
    "check",
    "fail-then-pass",
    "proof",
    "worktree",
    "recurring-findings"
  ],
  "userConfig": {
    "findings_buffer_adapter_repository": {
      "type": "directory",
      "title": "Findings-buffer adapter repository",
      "description": "Git common directory (git rev-parse --path-format=absolute --git-common-dir) of the one repository whose own findings-buffer adapter you trust. Applies in that repository's checkout and worktrees only. Unset: only adapters the plugin ships run."
    },
    "findings_buffer_adapter_path": {
      "type": "string",
      "title": "Findings-buffer adapter path",
      "description": "That repository's adapter directory, relative to the checkout root, holding executable append.sh and read.sh and a capabilities.json with schema_version 1.x. Set both options or neither. A path out of the checkout or into a nested repository is refused."
    }
  }
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 91 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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 Changed · +12 lines a79078ab6bbd
  2. 2d ago Changed 691e0934d7be
  3. 3d ago Changed 50fb7e38af84
  4. 4d ago First seen · 20 lines scan A e6b75651c043

Subscribe to this mod's changes

corrections is a plugin published in the GitHub repository melodic-software/claude-code-plugins (28 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-22.