agent-quality

agent-quality is a command for Claude Code from frankxai/agentic-creator-os. It costs 25 tokens per session (737 once invoked), scanned A, original, Apache-2.0.

An audit command that checks agent definition files against a nine-part quality rubric and ranks the ones needing attention.

In plain words
What is it for?
Use it to audit all agents, one named agent, or produce JSON for CI and other tools.
Why use it?
It replaces manual inspection with a consistent report showing which agents have structural problems and should be revised first.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is node scripts/agents/audit-agent-quality.mjs $ARGUMENTS.

Part of the agentic-creator-os plugin — 131 commands, 68 agents shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add frankxai/agentic-creator-os
Claude Code
/plugin install agentic-creator-os

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 131 commands, 68 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.

agentmods badge for agent-quality

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/agent-quality.svg)](https://agentmods.dev/commands/frankxai/agentic-creator-os/agent-quality)
Your own site
<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/agent-quality"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/agent-quality.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 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 5.1 $0.00025 $0.00737
Opus 5 $0.00013 $0.00368
Sonnet 5 $0.00005 $0.00147
Haiku 4.5 $0.00003 $0.00074

Measured 2d ago against content hash eb6f5852f304, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-quality 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/commands/agent-quality.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/agent-quality — ACOS Agent Quality Audit

Run the deterministic 9-check structural audit over every .claude/agents/*.md file. Surfaces which agents need revision first.

This is the slash-command surface for the audit. The @meta-agent-quality-auditor subagent uses the same script.

Workflow

1. Determine scope

If $ARGUMENTS is empty → audit all agents. If $ARGUMENTS is --json → output JSON for tooling/CI. If $ARGUMENTS is an agent name (e.g., meta-acos-router) → audit just that one.

2. Run

node scripts/agents/audit-agent-quality.mjs $ARGUMENTS

Equivalent invocations:

  • npm run agents:quality — full audit, writes report
  • npm run agents:quality:json — JSON to stdout (CI-friendly)

3. Report

The script writes two artifacts:

  • docs/acos/agent-quality-audit-<date>.md — human-readable ranked report
  • .frankx/machine/agent-quality-audit-<date>.json — machine-readable snapshot

Console summary shows:

  • Total audited
  • Disqualified count (existential gate fail)
  • L99-ready count (score 9/9)
  • Mean score
  • Top 8 priority fixes

4. The 9-check rubric (what it scores)

  1. Frontmatter complete — name/description/tools/model (EXISTENTIAL)
  2. Description with triggers — ≥50 chars + auto-fire cues
  3. Tools minimality — every declared tool referenced in Process
  4. Template-v2 sections — ≥8 of 10 canonical sections
  5. Memory contract — Process has recall + remember
  6. Anti-patterns — ≥4 negation bullets in §8
  7. Brand voice clean — zero AI-slop hits (EXISTENTIAL)
  8. No Arcanean leak — zero quarantine matches in prose (EXISTENTIAL)
  9. Smoke fixture exists — tests/fixtures//smoke.mjs present

5. When to dispatch the agent instead

Use @meta-agent-quality-auditor (subagent) instead of /agent-quality (slash) when:

  • The audit is part of a larger orchestrated flow
  • You want the result to come back as a structured JSON for downstream tooling
  • You need the audit to run with memory recall (subagent does step 0 memory load)

Read the full file on GitHub · 73 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. 2d ago First seen · 73 lines · 25 tokens per session scan A eb6f5852f304

Subscribe to this mod's changes

agent-quality is a command published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 737 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 2026-09-03.