narrator-ai-cli: Instructions file for Codex

AGENTS.md

narrator-ai-cli AGENTS.md is an instructions file for Codex, OpenCode from NarratorAI-Studio/narrator-ai-cli. It costs 8,023 tokens per session, scanned A, original, MIT.

A project instruction file for NarratorAI-Studio repositories that records GridLtd organization rules, team identities, coding standards, and Git workflow. It tells an agent how this organization’s projects and people should be handled.

In plain words
What is it for?
Use it when working on NarratorAI-Studio code, looking up team members, assigning GitHub work, sending Feishu or email messages, and following the organization’s development process.
Why use it?
It prevents mistakes such as using the wrong identifier for a teammate, editing a centrally managed file, or breaking the required branching and communication rules.

Instructions file for CodexOpenCode

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

This is NarratorAI-Studio/narrator-ai-cli's own configuration. It tells Codex and OpenCode how to work on narrator-ai-cli 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 narrator-ai-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NarratorAI-Studio/narrator-ai-cli. 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/NarratorAI-Studio/narrator-ai-cli/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/NarratorAI-Studio/narrator-ai-cli

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 narrator-ai-cli AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/narratorai-studio/narrator-ai-cli/agents-md.svg)](https://agentmods.dev/instructions/narratorai-studio/narrator-ai-cli/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/narratorai-studio/narrator-ai-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/narratorai-studio/narrator-ai-cli/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,023 This file is loaded in full into every session.
When invoked 8,023 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 $0.08023 $0.08023
Opus 5 $0.04012 $0.04012
Sonnet 5 $0.01605 $0.01605
Haiku 4.5 $0.00802 $0.00802

Measured 7d ago against content hash 88f706dea86a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

narrator-ai-cli 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 7d 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 · 669 lines

How it starts

The opening of the file, as written. The whole thing — 669 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GridLtd Organization Rules

This file is auto-synced to all repositories across the enterprise. Do not edit directly — update the source at Gridltd-DevOps/.github/org-rules.md

Team Directory

When you need to look up team members, fetch the current internal team directory before acting:

gh api repos/Gridltd-DevOps/.github/contents/team/members.yml -q '.content' | base64 -d

Identity rules:

  • github is the stable GitHub login. Use it for GitHub operations: assign issues/PRs, request reviews, mention users, CODEOWNERS, branch/commit attribution checks.
  • lark_open_id is the stable Feishu/Lark user id. Use it for Feishu direct messages or user mentions.
  • email is the stable email destination. Use it for mail only.
  • github_name is GitHub display metadata and is not stable or guaranteed unique.
  • alias, name, role, responsibility, and profile are human-readable metadata only; never use them directly as external action identifiers.

If the user gives only a name, alias, display name, role, or other ambiguous human label, resolve it against team/members.yml first. If more than one member matches, or if the match depends on memory rather than the current file, pause and ask the user to confirm the exact github, lark_open_id, or email before taking any external side effect.

Preferred deterministic resolver:

python .github/workflows/scripts/members/resolve_team_member.py --members-file team/members.yml --query "<name-or-alias-or-login>"

Use --check before changing the directory or agent identity rules:

python .github/workflows/scripts/members/resolve_team_member.py --members-file team/members.yml --check

Organization Standards

Communication

  • Communicate in Chinese, keep technical terms in English
  • Commit messages and PR descriptions must be in English

Git Flow Branching Model

Branch Purpose Merges to
main Production-ready code, always stable
develop Integration branch for features main (via release)
feature/<issue-id>-<short-desc> New features develop
release/<version> Release preparation & QA main + develop
hotfix/<issue-id>-<short-desc> Urgent production fixes main + develop

Read the full file on GitHub · 669 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. 7d ago First seen · 669 lines · 8,023 tokens per session scan A 88f706dea86a

Subscribe to this mod's changes

narrator-ai-cli AGENTS.md is an instructions file published in the GitHub repository NarratorAI-Studio/narrator-ai-cli (127 stars, last pushed 1mo ago), licensed MIT. It adds 8,023 tokens to every session, about $0.0401 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 2026-08-30.

Related

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens