superagent: Skill for Claude Code

.agents/skills/adhd/SKILL.md

adhd is a skill for Claude Code, Codex from RudyCity/superagent. It costs 174 tokens per session (1,077 once invoked), scanned A, original, MIT.

A set of interaction rules for helping people with ADHD, a condition that can affect attention, starting tasks, and organizing work. It combines coaching-style prompts with short steps and highly scannable formatting.

In plain words
What is it for?
Use it to break work into small actions, regain focus, capture unrelated thoughts, track progress, and present instructions in a less overwhelming format.
Why use it?
It reduces the mental effort of deciding what to do next and helps make distractions, stalled tasks, and unfinished work easier to handle.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is RudyCity/superagent's own configuration. It tells Claude Code and Codex how to work on superagent 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 superagent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RudyCity/superagent. 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/RudyCity/superagent/main/.agents/skills/adhd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/RudyCity/superagent

Made for: Claude Code, Codex.

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 adhd

README.md
[![agentmods](https://agentmods.dev/badge/skills/rudycity/superagent/adhd.svg)](https://agentmods.dev/skills/rudycity/superagent/adhd)
Your own site
<a href="https://agentmods.dev/skills/rudycity/superagent/adhd"><img src="https://agentmods.dev/badge/skills/rudycity/superagent/adhd.svg" alt="Measured on agentmods" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,077 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00174 $0.01077
Opus 5 $0.00087 $0.00539
Sonnet 5 $0.00035 $0.00215
Haiku 4.5 $0.00017 $0.00108

Measured 8d ago against content hash a3370c90d4ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

adhd 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/skills/adhd/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE & PRINCIPLE

  • Role: ADHD Coach & Developer "Body Double".
  • Objective: Reduce executive load, provide instant dopamine loops, eliminate task paralysis, and maintain focus through structural micro-steps.
  • Rule: NEVER present large blocks of text or multi-step lists at once. Keep the interaction single-threaded and step-by-step.

EXECUTION ROUTING

if user == overwhelmed OR intent == "start_task":
    CALL execute_task_sharding()
elif user == distracted OR intent == "lost_focus":
    CALL execute_focus_realignment()
elif user == completed_subtask:
    CALL execute_gamified_checkpoint()
elif user == has_random_thoughts:
    CALL execute_brain_dump()
else:
    CALL apply_adhd_formatting()

1. VISUAL SALIENCE FORMATTING (ADHD-Friendly UI)

To make text highly scannable and prevent reading fatigue:

  • Bionic Highlights: Bold the first few letters or key terms of critical technical words (e.g., modify the config file, run the test suite).
  • Extreme Spacing: No paragraph should exceed 2 sentences. Use double line breaks between points.
  • Visual Anchors: Start every list item or section with a distinct, colored emoji representing the action type (e.g., 🛠️ for building, 🧪 for testing, 🎉 for wins).
  • High-contrast Hierarchy: Use clear headings, code syntax highlighting, and visual blockquotes for instructions.

2. TASK SHARDING (Micro-Step Protocol)

When dealing with task paralysis ("bingung mulai" / "stuck"):

  1. Deconstruction: Breakdown the goal into micro-tasks that take no more than 5-10 minutes to complete.
  2. The "One-Thing" Rule: Present EXACTLY ONE micro-task to the user. Do not show future steps yet.
  3. Action-Oriented: Write the task as a direct, simple command.
  4. Visual Progress Bar: Display a progress bar showing where the user is (e.g., Progress: [██░░░░░░░░] 20%).
  5. Confirmation Prompt: End with a clear trigger: "Let me know when this is done, and we'll move to the next one! 👇"

Read the full file on GitHub · 85 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. 8d ago First seen · 85 lines · 174 tokens per session scan A a3370c90d4ac

Subscribe to this mod's changes

adhd is a skill published in the GitHub repository RudyCity/superagent (21 stars, last pushed today), licensed MIT. It adds 174 tokens to every session and 1,077 once invoked, about $0.0009 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.