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/readme)<a href="https://agentmods.dev/commands/enovatr-labs/specroute/readme"><img src="https://agentmods.dev/badge/commands/enovatr-labs/specroute/readme/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/readme"><img src="https://agentmods.dev/badge/commands/enovatr-labs/specroute/readme.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 | $0.00000 | $0.00462 |
| Opus 5 | $0.00000 | $0.00231 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
README 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 9d 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.
What it actually says
.claude/commands/ - Claude Code slash commands
Drop your project's slash commands here. Each command is a flat <name>.md file with YAML frontmatter and a body. Users invoke as /<name>.
File shape
---
description: <one-line description shown in /help>
---
<2–3 sentence overview of what this command does.>
## What this command does
- <Action 1>
- <Action 2>
## Implementation
```bash
# Inline shell commands. Deterministic - same input, same output.
echo "Running <command>..."
<your shell or python here>
Output
<What the user sees. Tables, status indicators, punch lists.>
See [`commands/command-template.claude.md`](../../../commands/command-template.claude.md) for the canonical template.
## When to build a command vs alternative
- Command: deterministic, no parameters or one well-defined arg, every invocation behaves the same.
- Skill: interactive, asks the user questions.
- Agent: autonomous, runs to completion.
- Hook: triggered by an event, not user-invoked.
See [`agentic-docs/automation-decision-framework.md`](../../../agentic-docs/automation-decision-framework.md) for the full matrix.
## Vendor support
As of mid-2026 all six vendors support custom commands, in their native shapes:
| Vendor | Command shape |
|---|---|
| Claude Code | `.claude/commands/<name>.md` (frontmatter + body) |
| Codex | a skill invoked via `/skills` or `$mention` |
| Gemini CLI | `.gemini/commands/<name>.toml` (`prompt` + `description`) |
| Kiro | a skill invoked via `/skill` (+ manual steering) |
| Cursor | `.cursor/commands/<name>.md` |
| Devin Desktop | a skill under `.devin/skills/<name>/SKILL.md`, invoked as `/<name>` |
When mirroring to Codex, convert to a skill folder under `.codex/skills/<slug>/SKILL.md`. See [`review-spec.md`](review-spec.md) for a worked example command.
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.
- 9d ago First seen · 57 lines · 0 tokens per session scan A a20c3d3a979d
README is a command published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 462 tokens. 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-apply
Implement SDD tasks — writes code following specs and design.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
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.