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.
git clone --depth 1 https://github.com/AG-Dmitry/composer-enhancedWrote 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.
[](https://agentmods.dev/rules/ag-dmitry/composer-enhanced/01-intake-decompose)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.00474 |
| Opus 5.5 | $0.00010 | $0.00190 |
| Sonnet 5.5 | $0.00005 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
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 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.
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
-
Restate the goal in one sentence, in your own words. If your restatement differs from what the user likely meant, ask before proceeding.
-
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.
-
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.
-
List explicit non-goals / out of scope to prevent scope creep later.
-
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.
-
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.
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 · 54 lines · 26 tokens per session scan A 463173ae4099
01-intake-decompose is a cursor rule published in the GitHub repository AG-Dmitry/composer-enhanced (3 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 474 once invoked, about $0.0001 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 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.