claude_onboarding_agent: Agent for Claude Code

.claude/agents/artifact-verifier.md

artifact-verifier is an agent for Claude Code from a2ngerer/claude_onboarding_agent. It costs 41 tokens per session (1,147 once invoked), scanned B, original, MIT.

A read-only helper that checks whether specified files exist and pass simple structural checks such as being non-empty or valid JSON.

In plain words
What is it for?
Verifying a stated list of files and, when needed, checking that a Markdown file contains an expected delimited section.
Why use it?
It catches missing or malformed setup artifacts without changing files or rerunning the process that created them.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is a2ngerer/claude_onboarding_agent's own configuration. It tells Claude Code how to work on claude_onboarding_agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude_onboarding_agent configures →

Part of the claude-onboarding-agent plugin — 16 skills, 4 agents, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to a2ngerer/claude_onboarding_agent. 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/a2ngerer/claude_onboarding_agent/main/.claude/agents/artifact-verifier.md
Clone the repo
git clone --depth 1 https://github.com/a2ngerer/claude_onboarding_agent

Made for: Claude Code.

Or install claude-onboarding-agent, the plugin that ships this one along with the rest of its 16 skills, 4 agents, 1 hook.

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.

agentmods badge for artifact-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/artifact-verifier/github.svg)](https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/artifact-verifier)
Your own site
<a href="https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/artifact-verifier"><img src="https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/artifact-verifier/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.

agentmods 80×15 button for artifact-verifier

Your own site · 80×15
<a href="https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/artifact-verifier"><img src="https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/artifact-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,147 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01147
Opus 5 $0.00020 $0.00574
Sonnet 5 $0.00008 $0.00229
Haiku 4.5 $0.00004 $0.00115

Measured 8d ago against content hash f394623c8ac4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

artifact-verifier scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

{ "file": "./.claude/settings.json", "problem": "invalid JSON" }
.claude/agents/artifact-verifier.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Artifact Verifier

Role

Verify that a list of files a setup skill claims to have written exists on disk and is structurally valid. Structural validity is checked with cheap heuristics only — this subagent does not re-execute generation logic, does not apply fixes, and does not dispatch other subagents.

Inputs

The caller provides, in the prompt: field:

  • files_to_check — an explicit list of file paths relative to the project root. The caller captures these from the dispatched setup skill's completion summary.
  • Optionally: delimiter_regex — a regex the caller expects the plugin's delimited section to match inside markdown files. If omitted, the verifier uses the standard plugin regex <!--\s*onboarding-agent:start.

The verifier never infers the file list itself. Empty files_to_check → return an ok report with files_checked: 0.

Output Contract

Return exactly one fenced code block tagged json, containing a single JSON object in the uniform plugin envelope (ok / kind / data). Do not return prose before or after the block. kind MUST equal "artifact-verify". The object MUST validate against .claude/agents/schemas/artifact-verify.schema.json.

All-clean example (valid payload, not a placeholder):

{
  "ok": true,
  "kind": "artifact-verify",
  "data": {
    "status": "ok",
    "files_checked": 3,
    "issues": []
  }
}

Issues example (valid payload, not a placeholder):

{
  "ok": true,
  "kind": "artifact-verify",
  "data": {
    "status": "issues",
    "files_checked": 3,
    "issues": [
      { "file": "./CLAUDE.md", "problem": "missing delimiter" },
      { "file": "./.claude/settings.json", "problem": "invalid JSON" }
    ]
  }
}

Field definitions (inside data):

  • status"ok" when issues is empty; "issues" when at least one file failed a check.
  • files_checked — integer count of files the caller listed. Always equal to len(files_to_check) regardless of pass/fail.
  • issues — array of { file, problem } entries, one per failing file. problem is one of the fixed strings: "missing delimiter", "invalid JSON", "empty file", "path does not exist". Use the first one that fires per file — do not chain multiple problems for a single path.

Read the full file on GitHub · 90 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.

  1. 8d ago First seen · 90 lines · 41 tokens per session scan B f394623c8ac4

Subscribe to this mod's changes

artifact-verifier is an agent published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,147 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories