ultracode: Instructions file for Claude Code

CLAUDE.md

ultracode CLAUDE.md is an instructions file for Claude Code from diepquynh/ultracode. It costs 1,317 tokens per session, scanned A, original, MIT.

A repository instruction file for Ultracode, a pipeline that generates agent configurations for several coding tools from shared source files. It sets rules for writing prompts, documentation, commands, and skills.

In plain words
What is it for?
It is for maintaining Ultracode's agents, commands, skills, and documentation, including checking prose and avoiding known formatting or workflow problems.
Why use it?
It keeps generated instructions consistent for both people and AI systems. It also records style rules and warnings about edits that can fail without obvious errors.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

This is diepquynh/ultracode's own configuration. It tells Claude Code how to work on ultracode 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 ultracode configures →

Reuse

Borrowing it

Nothing to install: this file belongs to diepquynh/ultracode. 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/diepquynh/ultracode/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/diepquynh/ultracode

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.

agentmods badge for ultracode CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/diepquynh/ultracode/claude-md/github.svg)](https://agentmods.dev/instructions/diepquynh/ultracode/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/diepquynh/ultracode/claude-md"><img src="https://agentmods.dev/badge/instructions/diepquynh/ultracode/claude-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 ultracode CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/diepquynh/ultracode/claude-md"><img src="https://agentmods.dev/badge/instructions/diepquynh/ultracode/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,317 This file is loaded in full into every session.
When invoked 1,317 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 $0.01317 $0.01317
Opus 5 $0.00659 $0.00659
Sonnet 5 $0.00263 $0.00263
Haiku 4.5 $0.00132 $0.00132

Measured 3d ago against content hash 1f15a9f40946, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ultracode CLAUDE.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 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.

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.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ultracode

A harness-neutral agent pipeline. One set of sources under agents/, commands/, and skills/ generates plugin trees for Claude Code, Codex, Grok Build, and Antigravity.

Writing style

Every .md in this repo is read by a model and by a person. Write for both. The whole file set was rewritten in plain language on 2026-09-02; keep it there.

Run the avoid-ai-writing skill on any prose you add to a prompt, a skill, a doc, or the README. Use edit mode, context docs, voice technical. The rules below are the ones that have come up here.

Mechanics

  • Em dash count is zero, including in headings. Use a colon, a period, or a comma.
  • Sentence case for headings.
  • Bold the rule name, not the sentence. One bolded span per paragraph at most.
  • Straight quotes.

No mannered prose

Mannered prose substitutes metaphor and flourish for direct statement. Instead of "a parameter worth varying," the mannered writer produces "a dial worth turning." Instead of "this point still matters," they write "this point earns its keep." The phrases exist to display the writer, not to convey the idea, and readers can tell. That is why mannered prose irritates: it makes the reader work harder so the writer can perform. It is also imprecise. Metaphors drag in connotations the writer did not choose and cannot control. The fix is to say what you mean. When a literal phrase is available, use it.

Prose

  • Lead with the instruction. Put the reason after it, in one sentence.
  • State what a thing is. Do not stack negations ("never X, never Y, never Z") for rhythm.
  • No superlatives standing in for a number. Write the cost, the count, or the failure.
  • No reassurance tails: "that is normal", "treat it as the method, not a budget cap", "not on principle".
  • Keep causal rationale. A model that knows why a rule exists applies it to cases the rule did not list. Cutting the "because" clause reads blunter and executes worse.
  • Cut hedges that change no action. Keep a frequency claim that is true and drives the next instruction.

Read the full file on GitHub · 96 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 Changed · +9 lines · +139 tokens per session 1f15a9f40946
  2. 7d ago First seen · 87 lines · 1,178 tokens per session scan A 787d789e8209

Subscribe to this mod's changes

ultracode CLAUDE.md is an instructions file published in the GitHub repository diepquynh/ultracode (4 stars, last pushed 3d ago), licensed MIT. It adds 1,317 tokens to every session, about $0.0066 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 2026-09-05.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

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

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

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