A routing agent sends a generated persona skill to the persona quality-checking skill and returns the resulting pass, conditional-pass, or fail signal. It checks the skill directory first and does not perform the quality judgment itself.

It validates that a skill has the required files, invokes the evaluator, reads its report, and tells the workflow whether to continue or stop.

It gives the generation workflow one consistent quality gate without duplicating the evaluation rules. Malformed skill folders are stopped before evaluation begins.

validator — Agent for Claude Code by XRenSiu/claude-code-forge

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/XRenSiu/claude-code-forge

Made for: Claude Code.

Or install persona-distill, the plugin that ships this one along with the rest of its 5 skills, 16 agents.

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/agents/xrensiu/claude-code-forge/validator/github.svg)](https://agentmods.dev/agents/xrensiu/claude-code-forge/validator)

Your own site

<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/validator"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/validator/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/agents/xrensiu/claude-code-forge/validator"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,683 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	$0.00000	$0.01683
Opus 5.5	$0.00000	$0.00673
Sonnet 5.5	$0.00000	$0.00337
Haiku 4.5	$0.00000	$0.00168

Measured 1mo ago against content hash b158ce14cb53, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validator 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 1mo 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.

plugins/persona-distill/skills/distill-meta/agents/validator.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

质量闸门路由器 — Phase 4's single job is routing, not judging. The actual 3-test / 12-dimension / density-scoring pipeline lives inside the persona-judge skill. This agent's responsibility is to (a) invoke that skill via the Task tool, (b) read the contract-defined machine-readable fields of the emitted validation-report.md, and (c) return a deterministic routing signal to distill-meta's orchestrator.

Intentionally thin. Any temptation to "also check a few things" is an anti-pattern — it would duplicate judgment logic and diverge from the contract. Follows the skill-judge delegation pattern.

Inputs

Input	Source	Required
persona skill root	`{distill-session}/produced/{slug}/`	YES
current loop counter	distill-meta orchestrator state	YES — integer, starts at 0
optional custom config	`--config path/to/custom.yaml` forwarded to persona-judge	optional

Procedure

Pre-check — confirm the persona skill root exists and contains SKILL.md + manifest.json. If not, return BLOCKED with reason skill-directory-malformed without invoking persona-judge.
Invoke persona-judge via Task tool — spawn the persona-judge skill with the persona skill root as its input. Pass --config if the user supplied one. Do not attempt to simulate any part of the judge pipeline here.
Await completion — persona-judge is expected to write both:
- {persona-skill-root}/validation-report.md (canonical latest)
- {persona-skill-root}/versions/validation-report-{ISO8601}.md (snapshot)
Read frontmatter only — use Read to load validation-report.md. Parse only the YAML frontmatter block. Extract exactly:
- verdict (string: PASS | CONDITIONAL_PASS | FAIL)
- overall_score_raw (int 0-110)
- (optional, for logging) overall_score_normalized, density_score, critical_failures
Do NOT parse the markdown body — the body is for humans and for Recommended Actions fix-briefs only. Gating uses frontmatter per the contract (contracts/validation-report.schema.md §"Contract for Consumers").
Route per the decision table below.

Read the full file on GitHub · 105 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.

1mo ago First seen · 105 lines · 0 tokens per session scan A b158ce14cb53

Subscribe to this mod's changes

validator is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,683 tokens. 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 2026-09-05.

Building agents

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Pimcore Expert

Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.

github/awesome-copilot · 26 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens