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.
npx agentmods add instructions/tanstack/devtools/agents-mdgit clone --depth 1 https://github.com/TanStack/devtoolsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00092 | $0.00092 |
| Opus 5 | $0.00046 | $0.00046 |
| Sonnet 5 | $0.00018 | $0.00018 |
| Haiku 4.5 | $0.00009 | $0.00009 |
Grade A, and why
devtools 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.
What it actually says
Agent Instructions
Before analyzing or changing this repository, read and follow
CONTRIBUTING.md. Its contribution, development, testing,
pull request, and changeset requirements apply to AI-assisted work as well as
human-authored work.
Keep every change focused on one topic. Understand and verify all generated code, run the required checks, and provide a concise pull request description that follows the repository template.
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.
- 2d ago First seen · 11 lines · 92 tokens per session scan A cf0b05fcc441
devtools AGENTS.md is an instructions file published in the GitHub repository TanStack/devtools (493 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session, about $0.0005 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.
Other instructions, from other repositories
rsc-boundary AGENTS.md
Instructions for foxted/rsc-boundary, covering agents.md — rsc boundary, purpose, layout, stack and commands (repo root).
ide-byebye AGENTS.md
Instructions for bo-516/ide-byebye, covering agents.md, structure & purity, module conventions, security (do not regress) and user-facing text & prompts.
why-did-you-render-mcp CLAUDE.md
Claude Code instructions for 0x1f320/why-did-you-render-mcp, covering why-did-you-render-mcp, architecture, packages, components and design decisions.
agent-virtual-office CLAUDE.md
Instructions for KbWen/agent-virtual-office, covering claude integration entry, startup (every conversation), slash commands, skills and validate.
agent-virtual-office copilot-instructions.md
Instructions for KbWen/agent-virtual-office, covering copilot repository instructions, always apply and useful paths.
agent-virtual-office GEMINI.md
Instructions for KbWen/agent-virtual-office, covering gemini integration entry, startup and review.