A plugin that checks whether an AI coding agent has changed tests to make a build appear successful. It flags deleted or skipped tests, weaker checks, and hardcoded outputs, then can block the agent's turn when it finds a serious problem.

Use it to review AI-generated changes and stop work when the agent tampers with the test suite or hides failures.

It helps prevent fake green builds caused by altering the tests instead of fixing the code.

proctor — Plugin by catfish-1234

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.

Claude Code

/plugin marketplace add catfish-1234/proctor

agentmods

npx agentmods add plugins/catfish-1234/proctor/plugin

Clone the repo

git clone --depth 1 https://github.com/catfish-1234/proctor

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

proctor 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.

plugin/.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "proctor",
  "displayName": "proctor",
  "version": "1.0.0",
  "description": "Catches AI coding agents gaming their test suites: deleting tests, skipping them, weakening assertions, or hardcoding outputs to fake a green build. Installs the honest-completion ruleset and a Stop hook that blocks a turn on any error-severity finding.",
  "author": {
    "name": "Kavish Dua",
    "url": "https://github.com/catfish-1234"
  },
  "homepage": "https://github.com/catfish-1234/proctor#readme",
  "repository": "https://github.com/catfish-1234/proctor",
  "license": "MIT",
  "hooks": "./hooks/claude-code.json",
  "keywords": [
    "testing",
    "test-tampering",
    "reward-hacking",
    "code-review",
    "git-hook",
    "guardrails"
  ]
}

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.

yesterday First seen · 24 lines scan A 67493e4ad654

Subscribe to this mod's changes

proctor is a plugin published in the GitHub repository catfish-1234/proctor (1 stars, last pushed 5d 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.

Code review Git and workflow Testing agent-skills ai claude-code-plugin cursor-plugin developer-tools gemini-cli-extension

proctor

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

domscribe

community

nowledge-mem-claude-code-plugin

nowledge-mem-copilot-cli-plugin

nowledge-mem-proma-plugin

posthog