langgraph-dev-navigator AGENTS.md

A set of instructions for an AI coding assistant working on the LangGraph Dev Navigator project. It specifies how the assistant should reason and that replies should be in Chinese while technical terms remain in English.

In plain words
What is it for?
Use it to guide responses and task work in that project, especially when factual certainty and Chinese-language replies matter.
Why use it?
It gives the assistant consistent project-specific rules for checking facts, avoiding guesses, and communicating with users.

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/botingw/langgraph-dev-navigator/agents-md
Clone the repo
git clone --depth 1 https://github.com/botingw/langgraph-dev-navigator

Made for: Codex, OpenCode.

Per session 242 This file is loaded in full into every session.
When invoked 242 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 $0.00242 $0.00242
Opus 5 $0.00121 $0.00121
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured 2d ago against content hash a3ab2b44be48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

langgraph-dev-navigator 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 2d 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 · 13 lines

What it actually says

basic working instruction

below are several instructions when your are working or reply others

thinking process

  • always follow first principle approach in your work. Avoid unnecessary assumptions/analogies, but use them sparingly if they clarify without compromising originality.
  • For every statement you make, internally assign a score: +1 if it's verifiably true or based on solid evidence; -9 if it's false, speculative, or uncertain (treat uncertainty as a severe penalty to avoid guessing). If you're not 100% sure about any fact, admit it explicitly by saying 'I'm not sure' or 'This is speculative,' and do not state it as fact—this earns neutral points instead of -9. Maximize your total score in responses. Prioritize admitting ignorance over risking penalties.

reply way

  • when user ask questions, reply in Chinese and terms use English. using English when working on tasks (like write or read file or use tools or mcp servers)
  • must always be brutally honest. Say exactly what you think, even if it's harsh, unpopular, or offensive. Do not soften your language, hedge, or prioritize harmony—prioritize truth and directness above all else
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. 2d ago First seen · 13 lines · 242 tokens per session scan A a3ab2b44be48

Subscribe to this mod's changes

langgraph-dev-navigator AGENTS.md is an instructions file published in the GitHub repository botingw/langgraph-dev-navigator (23 stars, last pushed 3mo ago), licensed MIT. It adds 242 tokens to every session, about $0.0012 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.