repair

repair is a command for Claude Code from danielraffel/generous-corp-marketplace. It costs 6 tokens per session (387 once invoked), scanned A, original, MIT.

A command for repairing broken Git worktree administration files. A Git worktree is a separate working directory connected to the same repository, and its administrative links can break if files or folders are moved.

In plain words
What is it for?
Use it with a worktree path when Git references, the .git file or related administrative data are broken. Afterward, check the worktree status.
Why use it?
It addresses worktrees that no longer work because their Git metadata or paths are corrupted. It also covers cases where the parent repository was moved.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the worktree-manager plugin — 8 commands shipped together

Good fit Use it with a worktree path when Git references, the .git file or related administrative data are broken. Afterward, check the worktree status.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/danielraffel/generous-corp-marketplace/repair
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/danielraffel/generous-corp-marketplace

Made for: Claude Code.

Or install worktree-manager, the plugin that ships this one along with the rest of its 8 commands.

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 repair

README.md
[![agentmods](https://agentmods.dev/badge/commands/danielraffel/generous-corp-marketplace/repair/github.svg)](https://agentmods.dev/commands/danielraffel/generous-corp-marketplace/repair)
Your own site
<a href="https://agentmods.dev/commands/danielraffel/generous-corp-marketplace/repair"><img src="https://agentmods.dev/badge/commands/danielraffel/generous-corp-marketplace/repair/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 repair

Your own site · 80×15
<a href="https://agentmods.dev/commands/danielraffel/generous-corp-marketplace/repair"><img src="https://agentmods.dev/badge/commands/danielraffel/generous-corp-marketplace/repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 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 $0.00006 $0.00387
Opus 5 $0.00003 $0.00193
Sonnet 5 $0.00001 $0.00077
Haiku 4.5 $0.00001 $0.00039

Measured 10d ago against content hash 35e81e3543d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

repair 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 10d 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.

plugins/worktree-manager/commands/repair.md · 65 lines

What it actually says

Worktree Repair Command

Repair broken or corrupted worktree administrative files.

Usage

/worktree-manager:repair <worktree-path>

Instructions for Claude

When user invokes this command:

  1. Parse arguments:

    • Extract worktree path (required)
  2. Call MCP tool:

    • Use mcp__worktree__worktree_repair
    • Pass worktree_path
  3. Display results:

    • Show repair status:
      • ✅ Worktree repaired:
    • Explain that administrative files have been updated
    • Suggest verifying with /worktree-manager:status
  4. Error handling:

    • Worktree doesn't exist → suggest using /worktree-manager:list
    • Not broken → inform user worktree is already functional
    • Permission errors → explain and suggest solutions

Examples

Repair worktree:

User: /worktree-manager:repair ~/worktrees/broken-feature
Claude: ✅ Worktree repaired: ~/worktrees/broken-feature
        Administrative files have been updated
        Verify with: /worktree-manager:status ~/worktrees/broken-feature

When to Use

Use this command when:

  • Worktree was manually moved and git references broke
  • Parent repository was moved
  • .git file is corrupted or has wrong paths
  • Git commands fail with "not a git repository" in a known worktree
  • After manually copying/moving the parent repository

What It Does

Repairs the connection between:

  • Worktree .git file → Parent repository
  • Parent repository → Worktree location
  • Updates all internal path references
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. 10d ago First seen · 65 lines · 6 tokens per session scan A 35e81e3543d6

Subscribe to this mod's changes

repair is a command published in the GitHub repository danielraffel/generous-corp-marketplace (11 stars, last pushed 11d ago), licensed MIT. It adds 6 tokens to every session and 387 once invoked, about $0.0000 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 2026-08-30.