Borrowing it
Nothing to install: this file belongs to cyberash-dev/veche. 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/cyberash-dev/veche/main/CLAUDE.mdgit clone --depth 1 https://github.com/cyberash-dev/vecheWrote 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/cyberash-dev/veche/claude-md)<a href="https://agentmods.dev/instructions/cyberash-dev/veche/claude-md"><img src="https://agentmods.dev/badge/instructions/cyberash-dev/veche/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/cyberash-dev/veche/claude-md"><img src="https://agentmods.dev/badge/instructions/cyberash-dev/veche/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 | $0.00464 | $0.00464 |
| Opus 5.5 | $0.00186 | $0.00186 |
| Sonnet 5.5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
veche 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 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.
What it actually says
CLAUDE.md
Project-level guidance for Claude Code sessions on this repository.
Read
AGENTS.mdfirst. It is the single source of truth for conventions (architecture, naming, SDD workflow, testing, CLI/Watch/install invariants, adapter gotchas, build-break rules). This file only adds what is genuinely Claude-Code-specific and does not repeat anything from there.
Tools to prefer in this repo
The spec is large (~10k lines, sharded across spec/partitions/*.md) and the source tree is
hexagonal with deep slices. Lean on semantic navigation rather than Read:
mcp__code-skeleton__get_outline— file outline before reading.LSP.goToDefinition/LSP.findReferences/LSP.hover— for "where is X" / "who calls Y" / "type of Z" questions.Read— only when you need exact bytes for anEdit.Grep— for string/log/literal searches; not for symbol lookups.
Handoff etiquette
- Diffs stay small and focused: one spec change ↔ one code change ↔ one test change.
- End-of-turn summary is one or two sentences (outcome + risk/follow-up). No essays.
- Don't open
README.md,AGENTS.md, orCLAUDE.mdunless the task explicitly asks for it.
Claude-Code-specific notes about this committee
This project's committee can be entered by a Claude Code orchestrator AND can
have Claude Code as a member. The recursion guard documented in AGENTS.md →
Recursion guard is what makes that safe. If you ever see a nested
start_meeting from a child process, something is wrong with the guard —
debug, don't paper over.
--bare on claude -p is opt-in via extraFlags, never default — it breaks
OAuth login for most users. The recursion guard relies on
--strict-mcp-config --mcp-config '{"mcpServers":{}}', not on --bare.
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 · 41 lines · 464 tokens per session scan A 9ce66eaca17f
veche CLAUDE.md is an instructions file published in the GitHub repository cyberash-dev/veche (21 stars, last pushed 5mo ago), licensed MIT. It adds 464 tokens to every session, about $0.0019 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.
veche CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| veche CLAUDE.mdcyberash-dev/veche | Instructions file | 21 | 5mo ago | MIT | A | 464 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |