A template for defining a specialized coding agent's responsibilities, owned files, working principles, boundaries, and trigger phrases.

Use it to create project-specific agent instructions and document which files and concerns each agent owns.

It prevents overlapping ownership and makes clear when an agent should handle a task or pass it to another agent.

<slug-lowercase-hyphenated> — Agent for Claude Code by Enovatr-Labs

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/agent-template.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/agent-template)

Your own site

<a href="https://agentmods.dev/agents/enovatr-labs/specroute/agent-template"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/agent-template.svg" alt="Measured on agentmods" height="20"></a>

Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,147 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.

Model	Per session	Once invoked
Fable 5.1	$0.00080	$0.01147
Opus 5	$0.00040	$0.00574
Sonnet 5	$0.00016	$0.00229
Haiku 4.5	$0.00008	$0.00115

Measured 8d ago against content hash 7ebee34ad0e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

<slug-lowercase-hyphenated> 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.

agents/agent-template.md · 60 lines

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.

You are the for - <one-sentence statement of the agent's authority and scope>.

Owns

<path/to/files> - <what's there and why this agent owns it>
<path/to/files> - <…>
<path/to/files> - <…>

List concrete file and directory ownership. Ownership is exclusive: two agents owning the same files is a coordination tax. Use the Don't use for section to hand off neighbors.

Operating principles

<Principle 1: a non-obvious rule the agent should follow. Be specific.>
<Principle 2.>
<Principle 3.>
<Principle 4: usually a "shape" rule, e.g. "every requirement has a stable ID" or "tasks must back-reference requirements".>
<Principle 5: usually a "scope" rule, e.g. "sample content uses generic domains only".>

These principles are the agent's brief. They override generic best-practice when in conflict.

Don't use for

<Adjacent concern 1> - .
<Adjacent concern 2> - .
<Adjacent concern 3> - .

Crisp boundaries here are how rosters stay healthy. If you find yourself violating "Don't use for," stop and hand off.

How to fill this template

Pick a slug. Lowercase, hyphen-separated. The filename matches the slug (e.g. prd-author.md).
Write the description with triggers. This is the most important field. Include 3–5 concrete trigger utterances in quotes - these drive automatic agent selection. Without triggers, the agent is invisible.
Pick a model - or don't. name and description are the only required fields; every other field below is optional. When model is absent, Claude Code subagents inherit the parent session's model, which is often the right answer. If you do set it, write a value your runtime accepts (Claude: opus / sonnet / haiku / fable / a full model id / inherit). SpecRoute's flagship / balanced / fast tiers are a documentation abstraction for rosters only - never write them into an agent file. Mapping table: wiki/Agents.md.
Decide on web access via tools. There is no internet: field - it is not read by any runtime. To let the agent research, include WebFetch / WebSearch in tools; to deny it, omit them from the allowlist or name them in disallowedTools.
Pick a color, optionally. Used by the runtime UI only. Nothing breaks if you omit it.
List Owns. Be specific about file paths and directories. The agent's claim to those files is exclusive.
Write 4–6 operating principles. Specific. Non-obvious. The kind of guidance you'd give a senior contributor on day one.
Write 2–4 "Don't use for" lines. These hand off the adjacent concerns to the right neighbor.
Body length. ~30–50 lines is the sweet spot. Longer agents tend to drift; shorter agents under-specify.

Read the full file on GitHub · 60 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.

8d ago First seen · 60 lines · 80 tokens per session scan A 7ebee34ad0e1

Subscribe to this mod's changes

<slug-lowercase-hyphenated> is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,147 once invoked, about $0.0004 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.

Autonomous Agents Building agents agentic-ai ai-coding ai-engineering developer-tools llmops

<slug-lowercase-hyphenated>

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Owns

Operating principles

Don't use for

How to fill this template

What this file has done since we first saw it

Other agents, from other repositories

graph-verifier

prometheus

atlas

generalist

hephaestus

oracle