ai AGENTS.md

Repository instructions that tell coding agents how to work on TanStack AI, including required guides and task-specific procedures.

In plain words
What is it for?
Following repository conventions, preparing bug fixes, editing documentation, handling issues, and creating pull requests.
Why use it?
They keep AI-assisted changes aligned with the project’s contribution rules and ensure documentation and pull requests follow the required process.

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/tanstack/ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/TanStack/ai

Made for: Codex, OpenCode.

Per session 1,968 This file is loaded in full into every session.
When invoked 1,968 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 $0.01968 $0.01968
Opus 5 $0.00984 $0.00984
Sonnet 5 $0.00394 $0.00394
Haiku 4.5 $0.00197 $0.00197

Measured 2d ago against content hash 81f22527de25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai 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 · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Read and follow CONTRIBUTING.md before analyzing or changing this repository. Its contribution and pull request requirements apply to AI-assisted work.

Cross-agent guidance for this repository. See CLAUDE.md for the full project overview, architecture, and conventions — this file mirrors the rules that apply to every coding agent regardless of tool.

Docs skill (mandatory for Claude, Grok, and Codex)

Before you plan, write, edit, or reorganize any file under docs/, you MUST load the docs skill and follow it. This is not optional.

Use the Skill tool if this harness has one. If it does not, Read .claude/skills/docs/SKILL.md (copies also live at .agents/skills/docs/SKILL.md for Codex and .grok/skills/docs/SKILL.md for Grok). Keep those three files identical.

Do not write docs from memory of this file. If you cannot load the skill, stop. Tiny copy edits still load the skill; the skill decides which gates to skip.

This also applies when planning a feature (include a doc-impact list) and when finishing a behavior change (docs must update before the work is done).

PR description skill (mandatory for Claude, Grok, and Codex)

Before gh pr create, and after an agent git push on a branch that already has an open PR, you MUST load the pr-description skill and follow it. This is not optional.

Use the Skill tool if this harness has one. If it does not, Read .claude/skills/pr-description/SKILL.md (copies also live at .agents/skills/pr-description/SKILL.md for Codex and .grok/skills/pr-description/SKILL.md for Grok). Keep those three files identical.

Do not invent a title and body from memory. If you cannot load the skill, stop. A human-only git push in another terminal does not trigger this.

A fix PR must pass bugfix-pr before this skill posts.

Bugfix PR skill (mandatory for Claude, Grok, and Codex)

Before you review, approve, open, or update a pull request that is a bug fix, you MUST load the bugfix-pr skill and follow it. This is not optional.

Read the full file on GitHub · 179 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. 2d ago First seen · 179 lines · 1,968 tokens per session scan A 81f22527de25

Subscribe to this mod's changes

ai AGENTS.md is an instructions file published in the GitHub repository TanStack/ai (3,045 stars, last pushed 2d ago), licensed MIT. It adds 1,968 tokens to every session, about $0.0098 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.