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.
/plugin marketplace add mickelsamuel/migrationpilotnpx agentmods add plugins/mickelsamuel/migrationpilot/claude-codegit clone --depth 1 https://github.com/mickelsamuel/migrationpilotGrade A, and why
migrationpilot 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 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.
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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "migrationpilot",
"displayName": "MigrationPilot",
"version": "1.5.1",
"description": "Blocks unsafe PostgreSQL migrations before they are written or run. Adds a migration-safety skill and a PreToolUse guardrail hook.",
"author": {
"name": "Mickel Samuel",
"email": "[email protected]",
"url": "https://github.com/mickelsamuel"
},
"homepage": "https://migrationpilot.dev",
"repository": "https://github.com/mickelsamuel/migrationpilot",
"license": "MIT",
"keywords": [
"postgresql",
"postgres",
"migration",
"database",
"safety",
"guardrail",
"zero-downtime",
"ddl"
],
"hooks": "./hooks/hooks.json"
}
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.
- yesterday First seen · 27 lines scan A d493a472df4c
migrationpilot is a plugin published in the GitHub repository mickelsamuel/migrationpilot (7 stars, last pushed 19d ago), 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 2026-08-31.
Other plugins, from other repositories
slop-chop
The slop-chop plugin: strip AI writing tells from text inside Claude Code.
slop-chop
Chop AI writing tells out of text. Wraps the slop-chop CLI so Claude can strip em-dashes, semicolons, and buzzwords, enforce a spelling dialect, or run the model rewrite pass on a draft.
skillcheck-free
Validates Claude Code SKILL.md files against 25 contract rules including structure, triggers, anti-patterns, and naming. Works with Claude Code, Claude Desktop/Web, and Cursor.
claudelint
Plugins for validating, linting, and improving Claude Code projects.
claudelint
A comprehensive linter for Claude Code projects. Validates CLAUDE.md files, skills, settings, hooks, MCP servers, plugins, and more. Requires: npm install --save-dev claude-code-lint.
valid-complete-fixture
A test fixture plugin with all valid configuration.