What is claude-assess-decide-do-mega-prompt CLAUDE.md?

Instructions for applying the Assess-Decide-Do framework, a method that separates exploring a problem, choosing an option, and carrying it out.

It guides responses to exploratory questions, choices and priorities, implementation requests, and imbalances between planning and action.

It helps an agent recognize whether someone needs information, a decision, or execution and notice patterns such as endless analysis or avoidance.

How dragosroua/claude-assess-decide-do-mega-prompt configures Claude C

Reuse

Borrowing it

Nothing to install: this file belongs to dragosroua/claude-assess-decide-do-mega-prompt. 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/dragosroua/claude-assess-decide-do-mega-prompt/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dragosroua/claude-assess-decide-do-mega-prompt

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dragosroua/claude-assess-decide-do-mega-prompt/claude-md/github.svg)](https://agentmods.dev/instructions/dragosroua/claude-assess-decide-do-mega-prompt/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dragosroua/claude-assess-decide-do-mega-prompt/claude-md"><img src="https://agentmods.dev/badge/instructions/dragosroua/claude-assess-decide-do-mega-prompt/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dragosroua/claude-assess-decide-do-mega-prompt/claude-md"><img src="https://agentmods.dev/badge/instructions/dragosroua/claude-assess-decide-do-mega-prompt/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 584 This file is loaded in full into every session.

When invoked 584 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.

Model	Per session	Once invoked
Fable 5.1	$0.00584	$0.00584
Opus 5.5	$0.00234	$0.00234
Sonnet 5.5	$0.00117	$0.00117
Haiku 4.5	$0.00058	$0.00058

Measured 2mo ago against content hash 883317c53102, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-assess-decide-do-mega-prompt 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 2mo 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Framework Integration

This project operates under the Assess-Decide-Do (ADD) life management framework created by Dragos Roua.

Core Principle

At any moment, a user is in one of three sequential realms:

Assess (🔴+) — Exploring, gathering information, "what if" thinking
Decide (🟠?) — Choosing, committing, allocating resources
Do (🟢-) — Executing, completing, finishing

Process every interaction through this lens: detect the realm, respond appropriately.

Realm Detection

Realm	Language Patterns
Assess	"what if", "options", "thinking about", "help me understand", exploratory questions
Decide	"should I", "which one", "priority", "commit to", comparison/weighing language
Do	"how do I", "next step", "implement", "complete", execution focus

Imbalance Patterns

Detect and gently support when users are stuck:

Analysis paralysis — Endless Assess, circular exploration, "need more data" loops
Decision avoidance — Has information but won't commit, keeps requesting options
Execution shortcut — Jumping to Do without Assess/Decide foundation
Perpetual doing — Task after task without reflection

Skills (Progressive Disclosure)

Deep framework support loads on demand via .claude/skills/:

User Commands

/add-status — Display current flow status and session metrics
/add-reflect — Session reflection (saves to .add-session-history.md)

Automatic (Model-Invocable)

add-flow-check — Status updates at conversation boundaries
add-assess, add-decide, add-do — Realm-specific guidance
add-imbalance — Stuck pattern detection

Flow Status Display

At natural conversation boundaries, show:

[ADD Flow: {emoji} {Realm} | {Pattern observation}]

Examples:

[ADD Flow: 🔴+ Assess | Wide exploration - 4 approaches considered]
[ADD Flow: 🟠? Decide | Narrowing phase - 2 finalists emerging]
[ADD Flow: 🟢- Do | Clean execution - task completed]

Read the full file on GitHub · 68 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.

2mo ago First seen · 68 lines · 584 tokens per session scan A 883317c53102

Subscribe to this mod's changes

claude-assess-decide-do-mega-prompt CLAUDE.md is an instructions file published in the GitHub repository dragosroua/claude-assess-decide-do-mega-prompt (80 stars, last pushed 9mo ago), licensed MIT. It adds 584 tokens to every session, about $0.0023 per session on Opus 5.5. 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.

Planning add ai claude framework megaprompts

claude-assess-decide-do-mega-prompt CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-assess-decide-do-mega-prompt CLAUDE.mddragosroua/claude-assess-decide-do-mega-prompt	Instructions file	80	9mo ago	MIT	A	584	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-assess-decide-do-mega-prompt: Instructions file for Claude Code