damage-control

A security system that intercepts tool calls before they run and blocks dangerous commands or access to protected files. Its rules can also prevent edits to lock files, generated files, and critical configuration.

In plain words
What is it for?
Use it to block commands such as recursive deletion, force-pushing Git changes, database removal, or cloud-resource deletion, and to protect secrets and system files.
Why use it?
It reduces the chance of deleting data, exposing credentials, changing protected files, or running destructive shell commands by accident. Protection depends on patterns defined in its configuration.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/thrownlemon/claude-code-plugins/damage-control
Any agent
npx skills add ThrownLemon/claude-code-plugins --skill damage-control
Clone the repo
git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 640 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 4 findings. Scan, not verified.
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 $0.00014 $0.00640
Opus 5 $0.00007 $0.00320
Sonnet 5 $0.00003 $0.00128
Haiku 4.5 $0.00001 $0.00064

Measured yesterday against content hash 68b66e933adc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

damage-control scanned grade D with 4 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 yesterday.

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.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

cat ~/.ssh/id_rsa

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://astral.sh/uv/install.sh | sh

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Block dangerous bash commands** - Prevents destructive operations like `rm -rf`, `git push --force`, database drops, cloud resource deletions

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -LsSf https://astral.sh/uv/install.sh | sh
plugins/damage-control/skills/damage-control/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Damage Control Security System

You are helping a user with the damage-control security plugin. This plugin provides defense-in-depth protection for Claude Code by intercepting tool calls before execution.

What This Plugin Does

The damage-control plugin uses PreToolUse hooks to:

  1. Block dangerous bash commands - Prevents destructive operations like rm -rf, git push --force, database drops, cloud resource deletions
  2. Protect sensitive files - Blocks access to secrets, credentials, and system files
  3. Guard against accidental modifications - Prevents edits to lock files, build outputs, and critical configs

Protection Levels

Level Read Write Edit Delete Examples
zeroAccessPaths Blocked Blocked Blocked Blocked ~/.ssh/, ~/.aws/, .env files, *.pem
readOnlyPaths Allowed Blocked Blocked Blocked /etc/, lock files, node_modules/
noDeletePaths Allowed Allowed Allowed Blocked .git/, LICENSE, README.md

Configuration

The protection patterns are defined in patterns.yaml. Users can customize:

  • bashToolPatterns: Regex patterns for dangerous commands
  • zeroAccessPaths: Files/directories with no access allowed
  • readOnlyPaths: Files that can be read but not modified
  • noDeletePaths: Files that can be modified but not deleted

Ask Patterns

Some patterns use ask: true to prompt for confirmation instead of blocking outright:

  • git checkout -- . (discards uncommitted changes)
  • git stash drop (permanently deletes a stash)
  • SQL DELETE with WHERE clause

Requirements

This plugin requires uv (Python package runner) to be installed:

curl -LsSf https://astral.sh/uv/install.sh | sh

Testing the Protection

Try these commands to verify the hooks are working:

# Should be blocked (dangerous command pattern: rm with -rf flags)
rm -rf /tmp/test

# Should be blocked (zero-access path: ~/.ssh/)
cat ~/.ssh/id_rsa

# Should prompt for confirmation (ask pattern: discards uncommitted changes)
git checkout -- .

Read the full file on GitHub · 89 lines

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. yesterday First seen · 89 lines · 14 tokens per session scan D 68b66e933adc

Subscribe to this mod's changes

damage-control is a skill published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 640 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 4 findings (reaches for credential files, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens