Graph-It-Live: Instructions file for Codex

AGENTS.md

Graph-It-Live AGENTS.md is an instructions file for Codex, OpenCode from magic5644/Graph-It-Live. It costs 929 tokens per session, scanned A, original, MIT.

Repository instructions for Graph-It-Live, a VS Code extension, command-line tool, and MCP server that analyses dependencies and call relationships in code. They define commands, coding rules, testing requirements, and architecture constraints.

In plain words
What is it for?
They are for maintaining Graph-It-Live, running its unit and end-to-end tests, checking coverage, packaging it, and making safe changes to its analyzer, MCP server, extension, or web view.
Why use it?
They give an agent the project's expected workflow and guardrails before it changes code, including how to build, test, format paths, and keep related components consistent.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is magic5644/Graph-It-Live's own configuration. It tells Codex and OpenCode how to work on Graph-It-Live itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Graph-It-Live configures →

Reuse

Borrowing it

Nothing to install: this file belongs to magic5644/Graph-It-Live. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/magic5644/Graph-It-Live/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/magic5644/Graph-It-Live

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 Graph-It-Live AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/magic5644/graph-it-live/agents-md/github.svg)](https://agentmods.dev/instructions/magic5644/graph-it-live/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/magic5644/graph-it-live/agents-md"><img src="https://agentmods.dev/badge/instructions/magic5644/graph-it-live/agents-md/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.

agentmods 80×15 button for Graph-It-Live AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/magic5644/graph-it-live/agents-md"><img src="https://agentmods.dev/badge/instructions/magic5644/graph-it-live/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 929 This file is loaded in full into every session.
When invoked 929 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00929 $0.00929
Opus 5.5 $0.00372 $0.00372
Sonnet 5.5 $0.00186 $0.00186
Haiku 4.5 $0.00093 $0.00093

Measured 22d ago against content hash cd0e2115cc83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Graph-It-Live 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 22d 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graph-It-Live Agent Guide

VS Code extension, standalone CLI, and MCP server for dependency and call-graph analysis. Requires Node.js 22+ and npm.

Commands

  • Build: npm run build; one test: npx vitest run <test-file>; unit suite: npm test.
  • Quality: npm run lint, npm run check:types, npm run test:coverage; E2E: npm run test:vscode.
  • Package: npm run package && npm run package:verify.

Prefix shell commands with rtk; use rtk proxy <command> when no optimized wrapper exists.

Core Principles

  • Simplicity First: make every change as simple as possible with minimal code impact.
  • No Laziness: find root causes; do not use temporary workarounds.
  • Minimal Impact: change only what is necessary and avoid introducing unrelated risk.

Universal Rules

  • Keep src/analyzer/** and src/mcp/** Node.js-only: never import vscode.
  • Define extension↔webview messages in src/shared/types.ts; update sender and receiver together.
  • Build paths with node:path; call normalizePath() before path keys enter Sets or Maps.
  • Keep TypeScript strict. Avoid any; ESLint decides style.
  • New functions/modules need success and edge/failure unit tests. User-facing behavior also needs VS Code E2E coverage. Touched files must stay at or above 80% coverage.
  • Never delete empty maps eagerly in ReverseIndex.removeDependenciesFromSource(); cleanup is query-time to avoid re-index races.
  • Build/dependency/package changes require production package validation: zero .map files and required WASM/query assets present.
  • After source changes, run targeted tests, lint, typecheck, and configured SonarQube analysis; fix findings caused by change.

Working Method

  • For exploration of .js, .jsx, .cjs, .mjs, .ts, .tsx, .cts, or .mts code, use Graph-It-Live MCP tools first (or graph-it scan and CLI fallback) before read_file, rg, or other direct source inspection. Use direct inspection afterward to verify details and edit safely.
  • Understand full flow and callers before editing. Fix root cause once.
  • For architecture, impact, or relationship questions, use the available Graph-It-Live MCP tools first; otherwise use the graph-it CLI. Run graph-it scan before analysis and after source changes.
  • Prefer deletion, existing helpers, standard library, platform features, and installed dependencies—in that order. Add no abstraction or dependency without need.
  • Make smallest complete diff; preserve unrelated code and APIs.

Read the full file on GitHub · 61 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. 22d ago Changed · +1 lines · +77 tokens per session cd0e2115cc83
  2. 23d ago Changed · +5 lines · +48 tokens per session 5ef0d4c9cd28
  3. 27d ago First seen · 55 lines · 804 tokens per session scan A 98ef3b79d1d9

Subscribe to this mod's changes

Graph-It-Live AGENTS.md is an instructions file published in the GitHub repository magic5644/Graph-It-Live (55 stars, last pushed today), licensed MIT. It adds 929 tokens to every session, about $0.0037 per session on Opus 5.5. 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 2026-09-11.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 6,805 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,680 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens