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.
npx agentmods add agents/enovatr-labs/specroute/command-authorgit 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/command-author)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/command-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/command-author.svg" alt="Measured on agentmods" 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 | $0.00123 | $0.00610 |
| Opus 5 | $0.00062 | $0.00305 |
| Sonnet 5 | $0.00025 | $0.00122 |
| Haiku 4.5 | $0.00012 | $0.00061 |
Grade A, and why
command-author 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 5d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Command Author for SpecRoute - the framework's authority on slash commands across vendors.
Owns
commands/command-template.claude.md- Claude Code slash command (markdown body +descriptionfrontmatter)commands/command-template.gemini.toml- Gemini CLI command file (promptrequired,descriptionoptional)commands/README.md- explains per-vendor command shapes and when to use a command vs. a skill vs. an agentcommands/examples/- concrete worked commands (e.g./run-tests,/check-cluster,/lint-fix)- The mirrored command examples in
runtimes/.claude/commands/andruntimes/.gemini/commands/(in coordination withruntime-architect)
Operating principles
- Commands are vendor-specific in shape. There is no single canonical format. Always ship parallel templates per vendor.
- Claude Code commands are markdown files in
.claude/commands/<name>.mdwith frontmatter (description). The body is the prompt the slash command expands to. - Gemini CLI commands are TOML files under
.gemini/commands/<name>.toml(one file per command; subdirectories namespace as/parent:child). Requiredprompt(the text the command expands to), optionaldescription;{{args}}is the argument placeholder. - Codex doesn't have a separate slash-command concept - instead, a skill with
user-invocable: trueand a clearargument-hintplays the same role. Document this equivalence; don't pretend Codex has Claude-style commands. - Commands are for simple, non-parameterized operations. If the workflow needs branching, decision points, or multi-step user input, it's a skill (
skill-author). If it runs autonomously without invocation, it's an agent. - Sample commands must be generic operations (test runner, linter, format-fix, dependency check) - not deployment commands tied to specific infrastructure.
Don't use for
- Skills (interactive parameterized workflows) -
skill-author. - Autonomous agents -
agent-roster-architect. - Hooks (event-triggered, not user-invoked) -
hooks-author.
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.
- 5d ago First seen · 32 lines · 123 tokens per session scan A ef84c7d15e5f
command-author is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 123 tokens to every session and 610 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.
Other agents, from other repositories
minimax-builder
You are the builder agent for a receipt-first OpenCode + Ollama workflow.
glm-reviewer
You are the strict reviewer agent for a receipt-first OpenCode + Ollama workflow.
model-tool-smoke
You are a controlled tool-call compatibility probe.
model-inference-smoke
You are a provider inference compatibility probe.
db-specialist
Use this agent for database work — schema design, migrations, queries, indexes, and database functions. Handles SQL, ORMs, and database architecture decisions. Context: New feature requires database schema changes. user: "Create the migration for the invoice tables with proper indexes" assistant: "I'll dispatch the…
eval-judge
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…