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/commands/enovatr-labs/specroute/command-template.claude)<a href="https://agentmods.dev/commands/enovatr-labs/specroute/command-template.claude"><img src="https://agentmods.dev/badge/commands/enovatr-labs/specroute/command-template.claude/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/commands/enovatr-labs/specroute/command-template.claude"><img src="https://agentmods.dev/badge/commands/enovatr-labs/specroute/command-template.claude.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 | $0.00040 | $0.00620 |
| Opus 5 | $0.00020 | $0.00310 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
command-template.claude 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 8d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<2–3 sentence overview of what this command does. Commands are simple, non-parameterized operations - if your idea has multiple modes or asks the user questions, it's a skill, not a command.>
What this command does
<Bullet list of concrete actions, in order:>
- <Action 1>
- <Action 2>
- <Action 3>
Implementation
# Inline shell commands the slash command runs.
# Keep this section deterministic - same input, same output, every time.
echo "── Running <command> ──"
<your shell or python here>
echo "── Done ──"
Output
<What the user sees. Make it scannable - tables, status indicators (✓ / ✗), or punch lists.>
When to use
- <Situation 1>
- <Situation 2>
Don't use for
- Operations with multiple modes - those are skills.
- Operations that require user input mid-flow - those are skills.
- Operations that should run automatically - those are hooks.
How to fill this template
-
Pick a slug. Lowercase, hyphen-separated. Filename is
<slug>.md. The slash command users type is/<slug>. -
Write the description. One concise line. This shows up in
/help. -
Write the body. Markdown explaining what the command does, followed by the actual implementation in a fenced code block. The body is the prompt that the slash command expands to - Claude Code interprets it.
-
Output is structured. Tables, status markers, punch lists. Don't make the user parse paragraphs.
-
Keep the frontmatter to
descriptionunless you need more. Claude Code's commands and skills have merged, so this file accepts the full skill frontmatter (argument-hint,allowed-tools,disallowed-tools,model,context: fork, and the rest - seeskills/skill-template/SKILL.md). Nothing is strictly required;descriptionis recommended because it is what the command list shows. Reach for the extra fields only when the command genuinely needs them - a command whose header grows a decision surface is a skill.
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.
- 8d ago First seen · 60 lines · 40 tokens per session scan A 6573dab7f6a9
command-template.claude is a command published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 620 once invoked, about $0.0002 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.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
atomic-plan
Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
review
Review the current diff against project memory.
statusline
Show the governor fleet in your Claude Code statusline. Explicit, opt-in, and chains — it never replaces an existing statusline.