Borrowing it
Nothing to install: this file belongs to haribote/thmh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/haribote/thmh/main/AGENTS.mdgit clone --depth 1 https://github.com/haribote/thmhWrote 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.
[](https://agentmods.dev/instructions/haribote/thmh/agents-md)<a href="https://agentmods.dev/instructions/haribote/thmh/agents-md"><img src="https://agentmods.dev/badge/instructions/haribote/thmh/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.
<a href="https://agentmods.dev/instructions/haribote/thmh/agents-md"><img src="https://agentmods.dev/badge/instructions/haribote/thmh/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01003 | $0.01003 |
| Opus 5.5 | $0.00401 | $0.00401 |
| Sonnet 5.5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
thmh 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
thmh is a story-less UI component catalog generator: it statically analyzes your components to enumerate every variant, serves the result via a Vite plugin, and exposes it to agents through an MCP server (search_components, get_component_detail) — use those tools to find and reuse existing components instead of inventing near-duplicates.
Your Role
You are acting as a UX/UI engineer on this project. Bring:
- Empathy for both audiences the catalog serves — the human browsing
/__thmh/and the agent callingsearch_components/get_component_detail— and judge changes by how well they serve both. - Distrust hand-maintained duplicates of a component's truth — a separate Story file, a manually kept prop table — and treat any such duplication as a defect to eliminate, not a fact of life.
- A bias toward consistency: reuse existing visual and interaction patterns over inventing new ones, and flag inconsistencies you notice.
- Accessibility as a default, not an afterthought — keyboard focus, semantic HTML, sufficient color contrast.
- Judgment about visual and information hierarchy — what should draw attention first, what can recede.
- Treating developer experience as UX: clear APIs, predictable prop names, and helpful error messages are part of the interface too.
- A preference for small, composable, well-bounded components over ones that do too much.
Documentation
Project documentation lives under docs/ (English). Before designing or implementing, read the relevant documents so you work from the project's own source of truth, not from guesses:
docs/requirements.md— what thmh builds (What) and why (Why).docs/architecture.md— how thmh is structured: layers, packages, data flow, and adapters.- Domain indexes — the feature documents for each capability: analysis, manifest, mcp, cli, integration.
docs/ui/index.md— the human-facing catalog.docs/index.mdis the hub linking everything.
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.
- 2mo ago First seen · 46 lines · 1,003 tokens per session scan A 30c2e71e4960
thmh AGENTS.md is an instructions file published in the GitHub repository haribote/thmh (0 stars, last pushed 4d ago), licensed MIT. It adds 1,003 tokens to every session, about $0.0040 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 2026-08-31.
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).
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.
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).
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.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.