setup

A repository setup command that installs Proctor's Git pre-commit hook and shared rules for coding agents. A pre-commit hook checks changes before Git accepts a commit.

In plain words
What is it for?
Use it to set up Proctor, verify that its installed files have not drifted, and identify the files that should be committed.
Why use it?
It helps catch changes that break the repository's checks and keeps agent rules installed and consistent across supported agents.

Command

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 commands/catfish-1234/proctor/setup
Clone the repo
git clone --depth 1 https://github.com/catfish-1234/proctor
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 341 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00025 $0.00341
Opus 5 $0.00013 $0.00170
Sonnet 5 $0.00005 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured yesterday against content hash 6b15059580ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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/commands/setup.md · 24 lines

What it actually says

Set proctor up in the current repository.

  1. Confirm this is a git repository. If it is not, stop and say so.
  2. Run npx @kavishdua/proctor install-hook to install the git pre-commit hook. This catches a bad change even when it did not come from an agent turn.
  3. Run npx @kavishdua/proctor install-skill to write the honest-completion ruleset to every supported agent's conventional path. Files proctor owns are written whole; shared instruction files like AGENTS.md are merged into a delimited block that leaves the rest of the file alone. Report which paths it wrote and which it merged.
  4. Run npx @kavishdua/proctor drift-check and confirm it exits 0.
  5. Tell the user which files to commit, including .proctor-adapter-manifest.json if it was created. That file is what lets drift-check tell a deleted ruleset apart from one that was never installed, so it needs to be committed alongside the rest.

The Stop hook is already active through this plugin, so do not also run install-claude-hook unless the user wants proctor to keep working in repositories where the plugin is not installed.

Do not create a proctor.config.json unless the user asks. The defaults enable every check, and an empty config file only adds a thing to keep in sync.

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 · 24 lines · 25 tokens per session scan A 6b15059580ab

Subscribe to this mod's changes

setup is a command published in the GitHub repository catfish-1234/proctor (1 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 341 once invoked, about $0.0001 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 2026-08-31.