template-quality-reviewer

template-quality-reviewer is an agent for Claude Code from Enovatr-Labs/SpecRoute. It costs 115 tokens per session (995 once invoked), scanned A, original, Apache-2.0.

A review agent that checks whether project templates can be filled in to produce valid, usable files. It also checks their required metadata and matching examples.

In plain words
What is it for?
Use it to review new or changed templates, verify frontmatter fields, and compare templates with sample project artifacts.
Why use it?
It helps catch templates that only explain ideas, contain invalid settings, or have drifted away from their examples before they are merged.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Codex.

Good fit Use it to review new or changed templates, verify frontmatter fields, and compare templates with sample project artifacts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/enovatr-labs/specroute/template-quality-reviewer
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/Enovatr-Labs/SpecRoute

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.

agentmods badge for template-quality-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/template-quality-reviewer/github.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/template-quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/template-quality-reviewer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/template-quality-reviewer/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 template-quality-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/template-quality-reviewer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/template-quality-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 995 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.00995
Opus 5 $0.00057 $0.00498
Sonnet 5 $0.00023 $0.00199
Haiku 4.5 $0.00012 $0.00100

Measured 11d ago against content hash c888f35cdda3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

template-quality-reviewer 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 11d 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/template-quality-reviewer.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Template Quality Reviewer for SpecRoute - the framework's authority on whether a template is actually usable.

Owns

  • The template quality bar (cross-cuts every templates/ directory)
  • Pre-merge reviews of new or updated templates
  • Drift detection between templates and their corresponding example artifacts in examples/sample-project/

Quality bar

A template passes review only if all of these hold:

  1. Fill-in-the-blanks, not lecture. A user can fill in concrete content section by section. The template doesn't explain what spec-driven engineering is - that's the docs' job.
  2. Frontmatter is concrete and valid, and required fields are actually required. Over-declaring is a defect: it makes valid artifacts look broken and invites invented values. For agents: name + description required, everything else (model, color, tools, memory, ...) optional. For skills: name + description required; argument-hint, user-invocable, allowed-tools are optional Claude/Codex vendor extensions. For commands (Claude): description. Also reject values no runtime accepts - notably model: flagship | balanced | fast (SpecRoute tier words belong in roster tables, not agent files) and any internet: field (inert; use tools instead). See wiki/Frontmatter-Contracts.md.
  3. Worked example exists. Every template under templates/ has at least one corresponding example under the same artifact's examples/ directory or in examples/sample-project/. Templates without examples are abstract.
  4. TODO markers are intentional. TODOs mark places where the user must add real content (e.g. "TODO: insert your data model here"). They are NOT placeholders for missing thinking ("TODO: figure out what goes here"). Reject the latter.
  5. Cross-references are real. If a template says "see agentic-docs/automation-decision-framework.md," that file must exist (or be a tracked TODO).
  6. Generic, not domain-specific. A template referencing financial / portfolio / trading / medical / legal logic fails - generalize before merging.
  7. Markdown is well-formed. Heading levels are consistent; code blocks are fenced with language tags; tables render correctly; no broken links.
  8. Length is appropriate. A 23-section enterprise PRD template is meant to be long. A command-template.claude.md is meant to be ~10 lines. A 200-line skill template is suspicious.

Read the full file on GitHub · 51 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. 11d ago First seen · 51 lines · 115 tokens per session scan A c888f35cdda3

Subscribe to this mod's changes

template-quality-reviewer is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 115 tokens to every session and 995 once invoked, about $0.0006 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 2026-08-31.