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.
git clone --depth 1 https://github.com/catfish-1234/proctorWrote 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.
[](https://agentmods.dev/plugins/catfish-1234/proctor/plugin)<a href="https://agentmods.dev/plugins/catfish-1234/proctor/plugin"><img src="https://agentmods.dev/badge/plugins/catfish-1234/proctor/plugin/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.
<a href="https://agentmods.dev/plugins/catfish-1234/proctor/plugin"><img src="https://agentmods.dev/badge/plugins/catfish-1234/proctor/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 1mo 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.
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"
]
}
What it installs
The manifest is a name and a version. 2 commands travel with it, and installing the plugin installs all of them — 38 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 24 lines scan A 67493e4ad654
proctor is a plugin published in the GitHub repository catfish-1234/proctor (1 stars, last pushed yesterday), 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
posthog
Access PostHog analytics, feature flags, experiments, error tracking, and insights directly from your AI coding tool. Optionally capture Claude Code sessions to PostHog LLM Analytics.
posthog
Access PostHog analytics, feature flags, experiments, error tracking, and insights directly from Gemini CLI.
domscribe
Domscribe is a pixel-to-code development tool that maps running UI elements to their exact source locations, capturing runtime context (props, state, DOM) for handoff to coding agents via MCP.
dev-loop
Multi-agent orchestration grounded in an LLM wiki. /dev-loop:orchestrate splits one goal into a dependency graph of parallel Claude Code sessions, each in its own worktree, and supervises them natively on Orca (a tracked Task + Dispatch per phase, pushed workerdone / question / escalation events instead of polling, st.
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
wavedash
Build browser games, integrate the Wavedash SDK, and prepare builds for upload and publishing.