SpecRoute: Instructions file for Claude Code

AGENTS.md

SpecRoute AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Enovatr-Labs/SpecRoute. It costs 2,906 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for SpecRoute, which uses written specifications and defined artifact types to guide development. AGENTS.md is a shared instruction file for coding agents.

In plain words
What is it for?
Understanding the AGENTS.md convention, configuring compatibility with tools that read other filenames, and following SpecRoute’s specification-driven workflow.
Why use it?
They explain how different agent tools load the instructions and establish one authoritative project context.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PreToolUse hook event, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is Enovatr-Labs/SpecRoute's own configuration. It tells Claude Code, Codex and OpenCode how to work on SpecRoute itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SpecRoute configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Enovatr-Labs/SpecRoute. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Enovatr-Labs/SpecRoute/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoute

Made for: Claude Code, Codex, OpenCode.

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.

agentmods badge for SpecRoute AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/enovatr-labs/specroute/agents-md/github.svg)](https://agentmods.dev/instructions/enovatr-labs/specroute/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/enovatr-labs/specroute/agents-md"><img src="https://agentmods.dev/badge/instructions/enovatr-labs/specroute/agents-md/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.

agentmods 80×15 button for SpecRoute AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/enovatr-labs/specroute/agents-md"><img src="https://agentmods.dev/badge/instructions/enovatr-labs/specroute/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,906 This file is loaded in full into every session.
When invoked 2,906 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02906 $0.02906
Opus 5 $0.01453 $0.01453
Sonnet 5 $0.00581 $0.00581
Haiku 4.5 $0.00291 $0.00291

Measured 9d ago against content hash f5f008eebe7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

SpecRoute AGENTS.md 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.

AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical, vendor-neutral context file for SpecRoute. This is the single source of truth for every agent CLI working in this repository.

Not every CLI loads it automatically. Codex and Cursor read AGENTS.md natively; Claude Code does not - its documentation states plainly that it reads CLAUDE.md, not AGENTS.md - and Gemini CLI does not either, since it reads GEMINI.md and only picks up AGENTS.md if you opt in through context.fileName. So CLAUDE.md and GEMINI.md are short delegation shims that pull this file in (an @AGENTS.md import, or a symlink). Blog posts claiming universal native AGENTS.md support are wrong; the shim is what makes it universal here.

About the AGENTS.md convention

AGENTS.md began as an OpenAI convention and is now stewarded by the Agentic AI Foundation under the Linux Foundation, with 60,000+ repositories using it. The convention specifies no required fields, no frontmatter, and no schema - it is plain Markdown, and its content is entirely up to the project. Nested AGENTS.md files are spec'd behaviour: an agent reads the nearest one up the directory tree.

What this repository is

SpecRoute is an open-source framework for spec-driven agentic software engineering, vendor-neutral across Claude Code, Codex, Gemini CLI, Kiro, Cursor, and Devin Desktop. It ships markdown content - templates, prompts, agent definitions, runtime layouts, and engineering rules - not application code.

There is no package manager, no build step, no test suite, no lint config. Do not look for package.json or run tests; treat this as a documentation/templates repository.

What "spec-driven" means here

The canonical flow is:

PRD → Spec (requirements + design + tasks) → Implementation → Validation → Review

Each stage has a template, an agent assignment, and an acceptance criterion. The point is not to slow work down - it's to make agent output reviewable. Code generation without a written spec is the failure mode this framework exists to prevent.

Read the full file on GitHub · 114 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.

  1. 9d ago First seen · 114 lines · 2,906 tokens per session scan A f5f008eebe7b

Subscribe to this mod's changes

SpecRoute AGENTS.md is an instructions file published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,906 tokens to every session, about $0.0145 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens