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.
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRouteWrote 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.
[](https://agentmods.dev/agents/enovatr-labs/specroute/template-quality-reviewer)<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.
<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>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 | $0.00115 | $0.00995 |
| Opus 5.5 | $0.00046 | $0.00398 |
| Sonnet 5.5 | $0.00023 | $0.00199 |
| Haiku 4.5 | $0.00012 | $0.00100 |
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 2mo 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.
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:
- 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.
- 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+descriptionrequired, everything else (model,color,tools,memory, ...) optional. For skills:name+descriptionrequired;argument-hint,user-invocable,allowed-toolsare optional Claude/Codex vendor extensions. For commands (Claude):description. Also reject values no runtime accepts - notablymodel: flagship | balanced | fast(SpecRoute tier words belong in roster tables, not agent files) and anyinternet:field (inert; usetoolsinstead). Seewiki/Frontmatter-Contracts.md. - Worked example exists. Every template under
templates/has at least one corresponding example under the same artifact'sexamples/directory or inexamples/sample-project/. Templates without examples are abstract. - 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.
- Cross-references are real. If a template says "see
agentic-docs/automation-decision-framework.md," that file must exist (or be a tracked TODO). - Generic, not domain-specific. A template referencing financial / portfolio / trading / medical / legal logic fails - generalize before merging.
- Markdown is well-formed. Heading levels are consistent; code blocks are fenced with language tags; tables render correctly; no broken links.
- Length is appropriate. A 23-section enterprise PRD template is meant to be long. A
command-template.claude.mdis meant to be ~10 lines. A 200-line skill template is suspicious.
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.
- 2mo ago First seen · 51 lines · 115 tokens per session scan A c888f35cdda3
template-quality-reviewer is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 115 tokens to every session and 995 once invoked, about $0.0005 per session on Opus 5.5. 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.
Other agents, from other repositories
bootstrap
Use once per invocation, at the start of a new Hedgehog project, to land the workspace for whichever core planner selected at Phase 0 — the first real workspace this project gets, since init with no explicit core flag lands the shared agents/skills/build-graph payload and leaves the workspace to bootstrap. Reads the…
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.
Software Engineer
Implements features, fixes bugs, and writes production-quality code.
ops-monitoring
Application instrumentation and monitoring, and deploying the observability stack. Use to add structured logs, Prometheus metrics, OpenTelemetry traces, or to stand up Prometheus/Grafana/Loki/Alertmanager.
ops-deps
Audit and analysis of dependencies. Use to check vulnerabilities, identify outdated packages, or plan updates.
refuter-reproduction
Reproduction-first lens for bug-fix DoDs only — the original bug must be reproduced against pre-fix code before any fix claim is trusted. Read-only. Invoked only by mnm-verify, only when the DoD's Goal is a bug fix.