Vigilis AGENTS.md

Vigilis AGENTS.md is an instructions file for Codex, OpenCode from piyushpathakqa/Vigilis. It costs 930 tokens per session, scanned A, original, MIT.

Repository guidance for Vigilis, a testing system that creates, sorts, repairs, and verifies browser tests using Playwright, Cypress, or Selenium. It can run through an MCP server or command-line tool in GitHub Actions.

In plain words
What is it for?
Use it when developing or reviewing Vigilis, its MCP server, command-line tool, browser-test healing, deployment gates, or verification receipts.
Why use it?
It explains the project's architecture, status, roadmap, and testing workflow before changes are made.

Instructions file for CodexOpenCode

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/piyushpathakqa/vigilis/agents-md
Clone the repo
git clone --depth 1 https://github.com/piyushpathakqa/Vigilis

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 Vigilis AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/piyushpathakqa/vigilis/agents-md.svg)](https://agentmods.dev/instructions/piyushpathakqa/vigilis/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/piyushpathakqa/vigilis/agents-md"><img src="https://agentmods.dev/badge/instructions/piyushpathakqa/vigilis/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 930 This file is loaded in full into every session.
When invoked 930 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 $0.00930 $0.00930
Opus 5 $0.00465 $0.00465
Sonnet 5 $0.00186 $0.00186
Haiku 4.5 $0.00093 $0.00093

Measured 4d ago against content hash 2235a2770531, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Vigilis 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — context for AI assistants (Cursor, Claude Code, etc.)

Read this first. It orients you fast so you don't re-derive decisions already made. Cursor, Claude Code, and most agent tools auto-load this file.

What this project is

Vigilis is the trust layer for autonomous testing: a Claude agent that generates, triages, and self-heals Playwright/Cypress/Selenium tests — and seals every decision into a hash-chained, verifiable attestation receipt. Healing is the wedge; attestation is the product (see CLAUDE.md for the full thesis). It ships two ways from one core:

  • MCP server (vigilis-mcp on npm, packages/mcp) — drive it from Claude Desktop/Code
  • CLI (vigilis on npm, packages/cli) — drive it from CI

The whole loop runs as a deployment gate in GitHub Actions. Built by Piyush Pathak; open-core (MIT agent/CLI/MCP + a commercial governance cloud, apps/cloud).

Where to find things

Doc What's in it
docs/DESIGN.md Architecture, the four-behavior loop, every decision + rationale, stack
docs/STATUS.md Current state, what's done, what's next, how to resume — read before working
docs/ROADMAP.md Milestones M0–M4 mapped to Linear ticket IDs (TRE-22..45)
README.md Public-facing pitch, quickstart, architecture diagram

The one-sentence architecture

Define the QA tools once in @argus/core (a single Tool Registry), expose them twice (MCP server + CLI). One Claude agent loop, four behaviors: Author → Generate → Triage → Heal.

Conventions

  • Language: TypeScript, ESM ("type": "module"), strict tsconfig.
  • Monorepo: pnpm workspaces. Packages live in packages/*, apps in apps/*.
  • Build: tsup per package. Typecheck: tsc --noEmit. Test: Vitest. Lint: ESLint flat config.
  • Cross-package imports resolve to dist/ at runtime, but typecheck maps @argus/core to its source via paths in consumer tsconfigs (see packages/cli/tsconfig.json).
  • Models: defaults in packages/core/src/index.tsclaude-opus-4-8 (primary), claude-haiku-4-5 (fast); overridable via ARGUS_MODEL_* env vars.
  • Secrets: ANTHROPIC_API_KEY in .env (see .env.example). Never commit .env.

Read the full file on GitHub · 69 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 · 69 lines · 930 tokens per session scan A 2235a2770531

Subscribe to this mod's changes

Vigilis AGENTS.md is an instructions file published in the GitHub repository piyushpathakqa/Vigilis (5 stars, last pushed 16d ago), licensed MIT. It adds 930 tokens to every session, about $0.0047 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.

Related

Other instructions, from other repositories