rote CLAUDE.md

rote CLAUDE.md is an instructions file for coding agents from trevhud/rote. It costs 18,001 tokens per session, scanned C, original, Apache-2.0.

A set of instructions for rote, a command-line tool that turns an AI skill file into a runnable background workflow. The workflow can target systems such as DBOS, Temporal, or Inngest.

In plain words
What is it for?
Use it when developing, compiling, or adapting rote pipelines and their runtime-specific output.
Why use it?
It explains rote’s layered design and project rules so an AI coding assistant can change the compiler and runtime pieces without confusing their roles.

Instructions file

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.

agentmods
npx agentmods add instructions/trevhud/rote/claude-md
Clone the repo
git clone --depth 1 https://github.com/trevhud/rote

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 rote CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/trevhud/rote/claude-md.svg)](https://agentmods.dev/instructions/trevhud/rote/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/trevhud/rote/claude-md"><img src="https://agentmods.dev/badge/instructions/trevhud/rote/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 18,001 This file is loaded in full into every session.
When invoked 18,001 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
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 $0.18001 $0.18001
Opus 5 $0.09001 $0.09001
Sonnet 5 $0.03600 $0.03600
Haiku 4.5 $0.01800 $0.01800

Measured 3d ago against content hash df9658f0be12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

rote CLAUDE.md scanned grade C with 1 finding 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 3d 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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

trial unresolved — pinning either would silently send the loop to the
CLAUDE.md · 1,318 lines

How it starts

The opening of the file, as written. The whole thing — 1,318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — context for AI collaborators

This file is for Claude Code (and similar coding agents) working in the rote repository. Read it before making non-trivial changes. It captures the project's mental model, architectural invariants, gotchas, and the canonical examples you should imitate.

If you're a human reading this, you probably want README.md or CONTRIBUTING.md instead — this file is deliberately oriented toward an AI that needs a fast mental model before it starts editing code.


What rote is

rote is a CLI that takes an Anthropic-style Skill (a SKILL.md + references/) and compiles it into a runnable background pipeline:

  1. An LLM agent (itself defined as a skill at skills/rote-compile/) reads the source skill and applies a structured rubric.
  2. The agent produces a pipeline.yaml (runtime-agnostic IR) plus extracted Python modules and typed LLM-judge signatures.
  3. A runtime adapter (DBOS by default; Temporal, Cloudflare Workflows, DBOS-TS, and Inngest too; more planned) consumes the IR and emits the runtime's native code shape — a single main.py DBOS app, a workflow.py + activities.py pair for Temporal, a TypeScript WorkflowEntrypoint class plus wrangler.jsonc / package.json for Cloudflare, or an Inngest function app that mounts into an existing Node/Next.js service.

The result is a deterministic workflow that replaces a fuzzy 10-20 minute agent loop. That's the whole product in one paragraph.


Three-layer architecture

Every piece of code in this repo belongs to exactly one layer. Respect the layer boundaries — most of the project's value comes from keeping them clean.

Layer 1 — The compiler agent (the "brain")

  • Lives at: skills/rote-compile/
  • Consists of: a SKILL.md plus five rubric files (node-kinds.md, crystallization-heuristics.md, ir-schema.md, llm-judge-extraction.md, implementation.md)
  • What it does: classifies every step of a source skill into one of 5 node kinds, extracts deterministic procedures into Python modules, designs typed signatures for LLM-judge steps, and assembles the whole thing into a pipeline.yaml
  • Runs under: a pluggable driver layer (see Layer 2)

Read the full file on GitHub · 1,318 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. 3d ago First seen · 1,318 lines · 18,001 tokens per session scan C df9658f0be12

Subscribe to this mod's changes

rote CLAUDE.md is an instructions file published in the GitHub repository trevhud/rote (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 18,001 tokens to every session, about $0.0900 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.