Borrowing it
Nothing to install: this file belongs to boussadjra/vuestrata. 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/boussadjra/vuestrata/main/CLAUDE.mdgit clone --depth 1 https://github.com/boussadjra/vuestrataWrote 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/boussadjra/vuestrata/claude-md)<a href="https://agentmods.dev/instructions/boussadjra/vuestrata/claude-md"><img src="https://agentmods.dev/badge/instructions/boussadjra/vuestrata/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/boussadjra/vuestrata/claude-md"><img src="https://agentmods.dev/badge/instructions/boussadjra/vuestrata/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 | $0.01074 | $0.01074 |
| Opus 5.5 | $0.00430 | $0.00430 |
| Sonnet 5.5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
vuestrata 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 24d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Read AGENTS.md first. It is the canonical brief: repo map,
architecture rules, state ownership, what each gate catches, quality gates, and
the toolchain rules. This file only adds what is specific to working here with
Claude Code.
AGENTS.md is also the highest authority: where this file and it disagree,
AGENTS.md wins.
The one thing that trips people up
This project uses Vite+, not plain npm scripts. There are two CLIs:
vp <name>runs a built-in —vp check,vp install,vp exec,vp dlx.vpr <name>runs apackage.jsonscript orvite.config.tstask. It is exactlyvp run <name>, spelled shorter.
Six names exist in both places — dev, build, preview, lint, fmt,
test — and vp prints a note for those telling you the script exists. It is
worth heeding: three of the scripts do strictly more than the built-in.
| Script | What it adds over vp <name> |
|---|---|
vpr lint |
custom rules, MSW worker version check, docs link check |
vpr build |
vue-tsc --noEmit first |
vpr dev |
--port 3333 --host |
Use vpr for those six. check has no script, so vp check is right and
silent. Never pnpm, npm, yarn, bun, or npx; for one-off binaries,
vp dlx. There is no vp vitest or vp oxlint.
Slash commands
| Command | What it does |
|---|---|
/add-module |
Scaffold a CRUD domain module |
/add-page |
Add a page to an existing module |
/add-theme |
Scaffold a theme |
/add-component |
Scaffold a Ui* wrapper |
/add-icon-set |
Scaffold an icon provider |
/verify |
Run the right gates for what changed |
Verifying
vp check # format, lint, types
node scripts/lint/run-custom-rules.mjs # six project-specific rules
vpr test --run # includes test/unit/architecture/
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.
- 24d ago Changed · +4 lines · +55 tokens per session 334e18342640
- 2mo ago First seen · 90 lines · 1,019 tokens per session scan A 2aa55844a923
vuestrata CLAUDE.md is an instructions file published in the GitHub repository boussadjra/vuestrata (111 stars, last pushed 11d ago), licensed MIT. It adds 1,074 tokens to every session, about $0.0043 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.
vuestrata CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vuestrata CLAUDE.mdboussadjra/vuestrata | Instructions file | 111 | 11d ago | MIT | A | 1,074 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |