Borrowing it
Nothing to install: this file belongs to shapediver/AppBuilderSdk. 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/shapediver/AppBuilderSdk/development/CLAUDE.mdgit clone --depth 1 https://github.com/shapediver/AppBuilderSdkWrote 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/shapediver/appbuildersdk/claude-md)<a href="https://agentmods.dev/instructions/shapediver/appbuildersdk/claude-md"><img src="https://agentmods.dev/badge/instructions/shapediver/appbuildersdk/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/shapediver/appbuildersdk/claude-md"><img src="https://agentmods.dev/badge/instructions/shapediver/appbuildersdk/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 | $0.00777 | $0.00777 |
| Opus 5.5 | $0.00311 | $0.00311 |
| Sonnet 5.5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
AppBuilderSdk 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 today.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AppBuilderSdk
Repositories
- Two git repos: the root (
AppBuilderSdk, usually ondevelopment) andsrc/shared, a separate clone ofAppBuilderShared. Run shared git commands asgit -C src/shared .... The root commits only the shared pointer (<KEY>: shared update) plus app, tests andpublic/, aftersrc/sharedis committed. - Shared code also runs in AppBuilderIJewel3D.
src/shared/CLAUDE.mdloads its host rules when you work there. - New worktree: a SessionStart hook inits
src/sharedand writes.vscode/settings.json. Check outtask/<KEY>in both repos. viewer.local.tscan link../Viewer. Viewer bugs are fixed there and need a dev server restart. Runpnpm installwhen the installed viewer version differs frompackage.json.
Git
- Branch
task/<KEY>. Every commit message starts with the ticket (SS-10004: ...). git checkout -- <file>restores from the index. Usegit checkout HEAD -- <file>when the file is staged.
Line endings
The working tree is CRLF, git stores LF (autocrlf), and eslint enforces linebreak-style: CRLF. Edit with the Edit/Write tools. sed -i and plain Python writes produce LF and hundreds of lint errors, and Prettier (endOfLine: auto) does not repair them. In Python, write with newline='' and \r\n.
Checks (changed files only)
- Format:
npx prettier --write <files>(also organizes imports). Some untouched tests already failprettier --check; ignore those. - Lint:
npx eslint <files> - Typecheck:
npx tsc --noEmit -p .at the root (coverssrc/shared). Always run it after changingforwardReftype parameters or host elements (svgvsimg), or spreading arefonto a third-party component. Don't spread a union-typedrefonto a component that accepts one host type; narrow the ref at each host. - Unit test:
npx jest --config jest.config.mjs <path>. Tests live in__tests__next to the module; store tests need thejsdomenvironment header. jest.mockreplaces all exports. When you add a named export, find the suites thatjest.mockthat module, keep the real exports with...jest.requireActual(...), and run those suites too (orpnpm test, which CI runs).- E2E:
e2e-testingskill. Never the whole suite. Don't deploy or rerun e2e unless asked or/implementor/specruns it.
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.
- today First seen · 40 lines · 777 tokens per session scan A 0dbdde82f0e0
AppBuilderSdk CLAUDE.md is an instructions file published in the GitHub repository shapediver/AppBuilderSdk (15 stars, last pushed today), licensed MIT. It adds 777 tokens to every session, about $0.0031 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 2026-11-13.
AppBuilderSdk CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AppBuilderSdk CLAUDE.mdshapediver/AppBuilderSdk | Instructions file | 15 | today | MIT | A | 777 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 280k | 2d ago | MIT | A | 4,325 | Codex, OpenCode |