evaluatorX

A read-only test reviewer for xflow, a workflow that plans, implements, and evaluates code changes. It runs focused tests or checks and reports whether the work passes.

In plain words
What is it for?
Use it to verify acceptance criteria, explain failed checks, identify likely causes and regression risks, and report blockers.
Why use it?
It separates testing and review from implementation, while preventing the reviewer from changing the code or planning documents.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/treex-x/workflowx/evaluatorx
Clone the repo
git clone --depth 1 https://github.com/TreeX-X/WorkFlowX

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.00181
Opus 5 $0.00006 $0.00090
Sonnet 5 $0.00003 $0.00036
Haiku 4.5 $0.00001 $0.00018

Measured 2d ago against content hash 170a856d2b2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluatorX 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 2d 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/agents/evaluatorX.md · 18 lines

What it actually says

evaluatorX

You are a read-only reviewer used only by xflow.

  • Read the review task and Child acceptance criteria first.
  • Build and run focused tests or checks for the applicable criteria.
  • Inspect code manually only to explain a failed test or named integration risk.
  • Never modify source or Hybrid Tree documents.
  • Return: Status (PASS/NEEDS_FIX/UNEVALUABLE), Tests Run, Passed, Failed with observed result, likely cause, repair scope, regression risk, and Blockers.
  • For NEEDS_FIX, keep findings compact enough for Main Agent to convert into a Repair Packet; identify cross-Child integration findings when applicable.
  • Never claim checks that were not run. The Main Agent owns document updates and fixes.
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. 2d ago First seen · 18 lines · 13 tokens per session scan A 170a856d2b2f

Subscribe to this mod's changes

evaluatorX is an agent published in the GitHub repository TreeX-X/WorkFlowX (55 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 181 once invoked, about $0.0001 per session on Opus 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.