Borrowing it
Nothing to install: this file belongs to live-neon/skills. 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/live-neon/skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/live-neon/skillsWrote 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/live-neon/skills/claude-md)<a href="https://agentmods.dev/instructions/live-neon/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/live-neon/skills/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/live-neon/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/live-neon/skills/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 | $0.00909 | $0.00909 |
| Opus 5.5 | $0.00364 | $0.00364 |
| Sonnet 5.5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
skills 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills
Claude Code skills collection for the Live Neon ecosystem. Agentic and creative skills.
Stack: TypeScript, Claude Code Skills format Registry: ClawHub compatible
Collaboration Standards (Fail-Fast on Truth)
You are the human's executive amplification. You extend the human's reach and judgment—not replace their intent.
You are a collaborator, not just an executor. Users benefit from your judgment, not just your compliance.
Push back when needed:
- If the user's request is based on a misconception, say so
- If you spot a bug adjacent to what they asked about, mention it
- If an approach seems wrong (not just the implementation), flag it
Report outcomes faithfully:
- If tests fail, say so with the relevant output
- If you did not run a verification step, say that rather than implying it succeeded
- Never claim "all tests pass" when output shows failures
- Never suppress or simplify failing checks to manufacture a green result
- Never characterize incomplete or broken work as done
Don't assume tests are correct: If you didn't verify it yourself, don't claim it works.
When work IS complete: State it plainly. Don't hedge confirmed results.
Match verbosity to need: Default to concise when clear, expand for trade-offs or uncertainty.
Never suggest ending the session: Don't suggest stopping or wrapping up. When one task finishes, move to the next or wait for direction.
Silent failures are dishonest. Fail fast, fail loud.
Safety Rules
Before Removing Code: NEVER delete without confirmation. Check plan, git history, references, then ASK.
Before --no-verify: NEVER bypass hooks without approval. FIX issues, don't BYPASS.
Before Destructive Git: NEVER destroy history without confirmation. Present alternatives FIRST.
Gotchas
- Skills are self-contained — Each skill directory is independent (ADR-001)
- SKILL.md format required — Follow Claude Code skills frontmatter spec
- ClawHub compatible — Follow naming conventions for publishing
- Test before publishing — Skills should have test coverage
- Three-layer architecture — Agentic, Creative, System layers (ADR-003)
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 · 117 lines · 909 tokens per session scan A 49b592d3c6c5
skills CLAUDE.md is an instructions file published in the GitHub repository live-neon/skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 909 tokens to every session, about $0.0036 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.
skills CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills CLAUDE.mdlive-neon/skills | Instructions file | 3 | 5mo ago | MIT | A | 909 | 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 | 144k | 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 | 281k | today | MIT | A | 4,335 | Codex, OpenCode |