agentmods.dev

proctor AGENTS.md

proctor AGENTS.md is an instructions file for Codex, OpenCode from OrionArchitekton/proctor. It costs 550 tokens per session, scanned A, original, MIT.

Repository instructions for Proctor, a quality-assurance tool that checks AI automations whose results can vary between runs. It describes the project layout, how to start it, and how to validate changes.

In plain words
What is it for?
Use them when changing Proctor, especially its contract checks, drift classification, invoice-extraction test system, UiPath connections, workflows, dashboard, or demo.
Why use it?
They give coding agents the project context and the checks needed to avoid breaking a TypeScript project with several packages and applications.

Instructions file for CodexOpenCode

not rated 2 1mo ago A scan 550 tokens original MIT
View the source file OrionArchitekton/proctor
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 instructions/orionarchitekton/proctor/agents-md
Clone the repo
git clone --depth 1 https://github.com/OrionArchitekton/proctor

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for proctor AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/orionarchitekton/proctor/agents-md.svg)](https://agentmods.dev/instructions/orionarchitekton/proctor/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/orionarchitekton/proctor/agents-md"><img src="https://agentmods.dev/badge/instructions/orionarchitekton/proctor/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 550 This file is loaded in full into every session.
When invoked 550 The same file — it is already loaded in full.
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 $0.00550 $0.00550
Opus 5 $0.00275 $0.00275
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 4d ago against content hash febfaa229e6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proctor AGENTS.md 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 4d 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.

AGENTS.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — proctor

Repo Role

Proctor is a QA agent that regression-tests non-deterministic AI automations using behavioral contracts and drift classification. It is a public submission for UiPath AgentHack 2026 (Track 3: UiPath Test Cloud), MIT-licensed, built as a TypeScript/pnpm monorepo (Next.js dashboard, Vercel Workflow durability, vitest tests).

Layout

  • packages/engine/ — contract learner, runner/assertion engine, drift classifier
  • packages/shared/ — shared types and schemas
  • packages/sut-invoice/ — the system-under-test: a deliberately non-deterministic invoice-extraction agent
  • packages/uipath/ — UiPathGateway adapters (LocalGateway default; TestCloudGateway REST stubs)
  • workflows/ — durable Vercel Workflow definitions (pause/resume approval)
  • apps/web/ — Next.js dashboard (pnpm dev)
  • scripts/seed-demo.ts — keyless narrated demo (pnpm demo)

Start Here

  • README.md — what it does, quickstart, env vars, UiPath wiring
  • ARCHITECTURE.md — two-altitude design (UiPath governs, Workflow gives durability)
  • docs/submission/ — Devpost description and demo script

Validation

Run from the repo root (Node 20+, pnpm 9.12.0; pnpm install --frozen-lockfile first):

pnpm typecheck   # tsc --noEmit
pnpm test        # vitest unit suite
pnpm test:int    # vitest integration suite (pause/resume cycle)

Tests and the demo run keyless by default (PROCTOR_FAKE_LLM=1, PROCTOR_GATEWAY=local) — no ANTHROPIC_API_KEY or UiPath credentials needed.

Contribution Boundaries

  • This is a hackathon submission with a hard deadline (2026-06-29); keep changes small, scoped, and demo-safe.
  • Do not commit secrets or credentials; the keyless path must keep working with no env vars set.
  • packages/uipath/src/testcloud.ts TODOs are blocked on live UiPath credentials — do not invent response shapes for them.
  • Keep the UiPath/Proctor boundary intact: UiPath is the control plane, Vercel Workflow is the durability layer; neither replaces the other.

Read the full file on GitHub · 50 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. 4d ago First seen · 50 lines · 550 tokens per session scan A febfaa229e6a

Subscribe to this mod's changes

proctor AGENTS.md is an instructions file published in the GitHub repository OrionArchitekton/proctor (2 stars, last pushed 1mo ago), licensed MIT. It adds 550 tokens to every session, about $0.0028 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.

agent-testingai-agentshackathonqaregression-testingtest-automation
Related

Other instructions, from other repositories

qa-skills AGENTS.md

AGENTS.md instructions for fishzjp/qa-skills, covering agents.md — qa-skills 项目指令, 使命（所有工作的对齐点）, 战略路径：迭代飞轮, 北极星指标 and 评测三轨道（eval/）.

fishzjp/qa-skills · 946 tokens

qualflare-claude-code CLAUDE.md

Claude Code instructions for Qualflare/qualflare-claude-code, covering qualflare-ai — claude code plugin developer guide, what is this?, plugin structure, how to update skills or commands and keeping framework slugs in sync.

Qualflare/qualflare-claude-code · 796 tokens

antigravity-testing-kit GEMINI.md

Instructions for anhtester/antigravity-testing-kit, covering gemini ai - global automation agent rules, git pull restriction rule, browser rules (mandatory), 🖥️ viewport & mode and 🔄 thứ tự debug bắt buộc (playwright mcp).

anhtester/antigravity-testing-kit · 3,029 tokens

flowproof CLAUDE.md

Instructions for automators-com/flowproof, covering claude.md, what flowproof is, repository layout, commands and things that will fail ci if you get them wrong.

automators-com/flowproof · 1,368 tokens

perseus-amd-act-ii AGENTS.md

AGENTS.md instructions for tcconnally/perseus-amd-act-ii, covering agents.md, the agent this repo ships, repo map, ground rules for agents editing this repo and reproduce everything.

tcconnally/perseus-amd-act-ii · 769 tokens

agentbreak CLAUDE.md

Instructions for mnvsk97/agentbreak, covering claude code — agentbreak, what this repo is, quick commands, skill and verification.

mnvsk97/agentbreak · 155 tokens