defuddle

defuddle is a cursor rule for Cursor from galyarderlabs/galyarder-framework. It costs 71 tokens per session (921 once invoked), scanned A, original, MIT.

Rules for using the Defuddle command-line tool to turn web pages into cleaner Markdown by removing navigation and other clutter. The input also describes project-tracking, command-prefix and execution rules.

In plain words
What is it for?
Reading and analysing ordinary online documentation, articles, blog posts and other web pages supplied by a user.
Why use it?
Web pages often contain extra content that makes them harder for an agent to read and uses more context than necessary.

Cursor rule for Cursor

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 rules/galyarderlabs/galyarder-framework/defuddle
Clone the repo
git clone --depth 1 https://github.com/galyarderlabs/galyarder-framework

Made for: Cursor.

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 defuddle

README.md
[![agentmods](https://agentmods.dev/badge/rules/galyarderlabs/galyarder-framework/defuddle.svg)](https://agentmods.dev/rules/galyarderlabs/galyarder-framework/defuddle)
Your own site
<a href="https://agentmods.dev/rules/galyarderlabs/galyarder-framework/defuddle"><img src="https://agentmods.dev/badge/rules/galyarderlabs/galyarder-framework/defuddle.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 921 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00071 $0.00921
Opus 5 $0.00036 $0.00461
Sonnet 5 $0.00014 $0.00184
Haiku 4.5 $0.00007 $0.00092

Measured 5d ago against content hash eeb6bcfcf08b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

defuddle 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/defuddle.mdc · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

THE Agentic Company Framework GLOBAL PROTOCOLS (MANDATORY)

1. Token Economy: The RTK Prefix

The local environment is optimized with rtk (Rust Token Killer). Always use the rtk prefix for shell commands (e.g., rtk npm test) to minimize token consumption.

  • Example: rtk npm test, rtk git status, rtk ls -la.
  • Note: Never use raw bash commands unless rtk is unavailable.

2. Traceability: Linear is Law

No cognitive labor happens outside of a tracked ticket. You operate exclusively within the bounds of a project-scoped issue.

  • Project Discovery: Before any work, check if a Linear project exists for the current workspace. If not, CREATE it.
  • Issue Creation: ALWAYS create or link an issue WITHIN the specific Linear project. NEVER operate on 'No Project' issues.
  • Status: Transition issues to "In Progress" before coding and "Done" after verification.

3. Cognitive Integrity: Scratchpad Reasoning

Before executing any high-impact tool (write_file, replace, run_shell_command), it is standard protocol to output a <scratchpad> block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.

4. Technical Integrity: The industry experts Principles

Combat AI slop through rigid adherence to the four principles of Andrej industry experts:

  1. Think Before Coding: Don't guess. If uncertain, STOP and ASK. State assumptions explicitly. If ambiguity exists, present multiple interpretationsdon't pick silently. Push back if a simpler approach exists.
  2. Simplicity First: Implement the minimum code that solves the problem. No speculative abstractions. If 200 lines could be 50, rewrite it. No "configurability" unless requested.
  3. Surgical Changes: Touch ONLY what is necessary. Every changed line must trace to the request. Don't "improve" adjacent code or refactor things that aren't broken. Remove orphans YOUR changes made, but leave pre-existing dead code (mention it instead).
  4. Goal-Driven Execution: Define success criteria via tests-first. Loop until verified.
    • Multi-step tasks MUST use this syntax:
      1. [Step] verify: [check]
      2. [Step] verify: [check]

Read the full file on GitHub · 80 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. 5d ago First seen · 80 lines · 71 tokens per session scan A eeb6bcfcf08b

Subscribe to this mod's changes

defuddle is a cursor rule published in the GitHub repository galyarderlabs/galyarder-framework (22 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 921 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 2026-08-30.