01-intake-decompose

01-intake-decompose is a cursor rule for coding agents from AG-Dmitry/composer-enhanced. It costs 26 tokens per session (474 once invoked), scanned A, original, MIT.

A planning checklist for breaking a coding task into a clear, testable plan before writing code.

In plain words
What is it for?
Use it to restate a request, identify questions, define success checks, list non-goals, and classify the task's complexity.
Why use it?
It helps prevent solving the wrong problem by exposing unclear requirements, assumptions, scope limits, and the level of difficulty.

Cursor rule

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/ag-dmitry/composer-enhanced/01-intake-decompose
Clone the repo
git clone --depth 1 https://github.com/AG-Dmitry/composer-enhanced

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 01-intake-decompose

README.md
[![agentmods](https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/01-intake-decompose.svg)](https://agentmods.dev/rules/ag-dmitry/composer-enhanced/01-intake-decompose)
Your own site
<a href="https://agentmods.dev/rules/ag-dmitry/composer-enhanced/01-intake-decompose"><img src="https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/01-intake-decompose.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 474 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 $0.00026 $0.00474
Opus 5 $0.00013 $0.00237
Sonnet 5 $0.00005 $0.00095
Haiku 4.5 $0.00003 $0.00047

Measured 5d ago against content hash 463173ae4099, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

01-intake-decompose 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.

agent-protocols/01-intake-decompose.mdc · 54 lines

What it actually says

Phase 1 — Intake & Decompose

Persona: Planner. No code in this phase.

The single biggest cheap-model failure is solving the wrong problem confidently. Spend tokens here to avoid that.

Steps

  1. Restate the goal in one sentence, in your own words. If your restatement differs from what the user likely meant, ask before proceeding.

  2. List the unknowns and assumptions. Everything you do not know for a fact yet: unclear requirements, unverified APIs, ambiguous scope. Each item is either (a) something to verify in phase 2, or (b) a question for the user. Do not silently assume an answer.

  3. Define testable success criteria. Concrete, checkable statements such as:

    • "Function X returns Y for input Z."
    • "The test suite passes including a new test for the new behavior."
    • "No existing test breaks." These become the checklist you must satisfy before declaring done.
  4. List explicit non-goals / out of scope to prevent scope creep later.

  5. Classify complexity — this scales how much rigor later phases apply:

    • medium — localized, single file/area, clear path.
    • medium-high — multiple files, integration points, several edge cases.
    • high — cross-cutting/architectural, ambiguous, security- or performance-sensitive. Consider escalating a critic subagent early.
  6. Decompose the work into ordered, individually verifiable sub-steps.

Working memory

Create .cursor/agent-memory/<task-slug>.md from templates/task-memory.md and fill the Goal, Success criteria, Non-goals, Complexity, and Open questions sections now.

Exit criteria

  • Goal restated and confirmed (or question asked).
  • Success criteria written and testable.
  • Complexity classified.
  • Sub-steps listed.

Proceed to 02-context-grounding.mdc.

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 · 54 lines · 26 tokens per session scan A 463173ae4099

Subscribe to this mod's changes

01-intake-decompose is a cursor rule published in the GitHub repository AG-Dmitry/composer-enhanced (3 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 474 once invoked, about $0.0001 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 2026-08-31.