Borrowing it
Nothing to install: this file belongs to ahpxex/open-dashboard. 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/ahpxex/open-dashboard/main/CLAUDE.mdgit clone --depth 1 https://github.com/ahpxex/open-dashboardWrote 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/ahpxex/open-dashboard/claude-md)<a href="https://agentmods.dev/instructions/ahpxex/open-dashboard/claude-md"><img src="https://agentmods.dev/badge/instructions/ahpxex/open-dashboard/claude-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/ahpxex/open-dashboard/claude-md"><img src="https://agentmods.dev/badge/instructions/ahpxex/open-dashboard/claude-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 | $0.05320 | $0.05320 |
| Opus 5.5 | $0.02128 | $0.02128 |
| Sonnet 5.5 | $0.01064 | $0.01064 |
| Haiku 4.5 | $0.00532 | $0.00532 |
Grade A, and why
open-dashboard CLAUDE.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 1mo 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
What this is — read first
An AI-native, skill-driven back-office substrate (a "中台" template). The repo
is not a product. It is the source of truth for the skill catalogue
(.claude/skills/): one add-component skill — a catalogue + retriever over
35+ copy-ready admin UI shapes (CRUD, detail, master-detail, kanban, calendar,
wizard, billing, RBAC, i18n, …), each a reference doc + a generated template — plus
a handful of operation skills (scaffold-dashboard, add-backend,
rebrand). A Skills
Gallery renders every shape's own demo. The demos, the
resources, and the two business cases all exist for one reason: to back a shape
and be the live proof it produces working UI. A shape's distributed templates/
are generated from this repo's working source and kept byte-for-byte in sync, so
the catalogue never ships code the repo hasn't typechecked, built, and tested.
The stance is frontend-opinionated, backend-agnostic — preserve it. The frontend
is one fixed, curated stack you compose from (TanStack Start + the shape catalogue +
the UI / form / table / chart system on @base-ui) — be opinionated here. The backend
(business data and auth) is swappable behind two seams — Repository and
AuthProvider — never the frontend's concern: pick one of the add-backend presets
(Postgres + Drizzle + better-auth by default; or Hono / FastAPI / Supabase, with
Prisma / Auth.js / custom-JWT). The enforcing rule is mechanical: backend specifics
(@/db, @/lib/auth, drizzle-orm, pg, an SDK client) live only in server-only
modules (a resource's server.ts, src/db/*, src/lib/auth*.ts, the infra/data
adapters) and reach the client solely through createServerFn + the two seams. Don't
let a backend leak upward, and don't fork the frontend stack per project.
Two modes of work — know which you're in:
- Authoring the substrate — the default here. You're adding or fixing a
skill, the platform layer, a gallery demo, or a business case inside this
repo. Whatever you produce must (a) be real, working repo code — so it's
verified and visible in the gallery — and (b) stay in lockstep with its
distributed skill via
sync-skills. If you are editing files in this repo, you are almost certainly in this mode. → see Authoring a skill below. - Porting out. A different agent stands up a real product by scaffolding the
clean base into a new project and composing it (scaffold → rebrand → pick a
backend → add resources → add shapes). The base is demo-free + gallery-free, so
there's nothing to strip. That workflow lives in
PORTING.mdand thescaffold-dashboard/rebrand/add-backendskills — not here. Don't confuse "build a product" (port-out) with "maintain the substrate" (the work in this repo).
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.
- 1mo ago First seen · 276 lines · 5,320 tokens per session scan A efb2734fee1e
open-dashboard CLAUDE.md is an instructions file published in the GitHub repository ahpxex/open-dashboard (146 stars, last pushed 3mo ago), licensed MIT. It adds 5,320 tokens to every session, about $0.0213 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 2026-08-30.
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.
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.
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).