A validator for checking whether a project contains the expected Claude Code files, folders, configuration, documentation, Git setup, and memory files.

Use it to verify a generated project, including its CLAUDE.md file, settings, agent and skill directories, documentation, and required content.

It finds missing or malformed agent infrastructure before the project is considered ready.

How xeeva/Genesis configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to xeeva/Genesis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/xeeva/Genesis/main/.claude/skills/validate/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/xeeva/Genesis

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xeeva/genesis/validate/github.svg)](https://agentmods.dev/skills/xeeva/genesis/validate)

Your own site

<a href="https://agentmods.dev/skills/xeeva/genesis/validate"><img src="https://agentmods.dev/badge/skills/xeeva/genesis/validate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xeeva/genesis/validate"><img src="https://agentmods.dev/badge/skills/xeeva/genesis/validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 590 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00032	$0.00590
Opus 5.5	$0.00013	$0.00236
Sonnet 5.5	$0.00006	$0.00118
Haiku 4.5	$0.00003	$0.00059

Measured 2mo ago against content hash f9e21be41e2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validate 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.

.claude/skills/validate/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Validator

Check that a target project directory has all expected Claude Code infrastructure files and that they are well-formed.

Usage

The user provides a project name or path. Default to the most recently created project if none specified.

Checks

Required Files

CLAUDE.md exists and is non-empty
.claude/settings.json exists and is valid JSON
.claude/agents/ directory has at least 3 agent files (test-runner, code-reviewer, doc-writer)
.claude/skills/ directory has at least 4 skill directories (test, lint, review, commit)
Each skill directory contains a SKILL.md with valid YAML frontmatter
docs/README.md exists
docs/architecture.md exists
.gitignore exists
Git repo is initialised (.git/ exists)

Memory Files

~/.claude/projects/-home-xeeva-claude-<name>/memory/MEMORY.md exists
~/.claude/projects/-home-xeeva-claude-<name>/memory/user-profile.md exists
~/.claude/projects/-home-xeeva-claude-<name>/memory/project-context.md exists

Content Quality

CLAUDE.md contains "Australian English" rule
CLAUDE.md contains "em dash" rule
CLAUDE.md contains "fail fast" or error handling section
CLAUDE.md contains testing section
settings.json has permissions.allow array
settings.json has at least one hook

Optional Files

.mcp.json exists if integrations were specified (report if missing but expected)
Stack-specific config files exist (tsconfig.json, pyproject.toml, etc.)

Output

Report results as a checklist:

Validating: ~/claude/<name>/

Required Files:        [12/12 passed]
Memory Files:          [3/3 passed]
Content Quality:       [5/6 passed]
  - MISSING: settings.json has no hooks configured
Optional Files:        [2/2 passed]

Overall: 22/23 checks passed

If all checks pass: "Project is fully configured and ready to use." If checks fail: list the failures with specific remediation steps.

Read the full file on GitHub · 64 lines

Changes

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 · 64 lines · 32 tokens per session scan A f9e21be41e2b

Subscribe to this mod's changes

validate is a skill published in the GitHub repository xeeva/Genesis (17 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 590 once invoked, about $0.0001 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.

Claude Code Code Generation ai-agents anthropic claude developer-tools

evaluation-bigcode-evaluation-harness

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

davila7/claude-code-templates · 70 tokens

generate

Turn a codebase, an OpenAPI/gRPC/GraphQL spec, or a plain-language description of an API into a production-ready MCP server, using mcp-anything. Use when the user wants to expose software, an API, a CLI tool, or a service as MCP tools for Claude or other agents.

gabrielekarra/mcp-anything · 66 tokens

web-reading

Read complex or JavaScript-rendered web pages cleanly. When a plain URL fetch returns an empty shell, garbled HTML, or "enable JavaScript", re-fetch the page through Jina Reader (https://r.jina.ai/) to get rendered, LLM-ready Markdown. Keyless, no setup. Use whenever a fetched page looks broken or you need the real…

EpisodeYu/HarnessSmith · 82 tokens

Genesis: Skill for Claude Code