Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/madebyaris/cursor-composer-rulesnpx agentmods add rules/madebyaris/cursor-composer-rules/composer-coreWrote 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/madebyaris/cursor-composer-rules/composer-core)<a href="https://agentmods.dev/rules/madebyaris/cursor-composer-rules/composer-core"><img src="https://agentmods.dev/badge/rules/madebyaris/cursor-composer-rules/composer-core/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/madebyaris/cursor-composer-rules/composer-core"><img src="https://agentmods.dev/badge/rules/madebyaris/cursor-composer-rules/composer-core.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 | $0.01855 | $0.01855 |
| Opus 5.5 | $0.00742 | $0.00742 |
| Sonnet 5.5 | $0.00371 | $0.00371 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
composer-core 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 26d 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composer core
How to change code and continue an app, in priority order. These principles override habits and shortcuts. Programming-first: most turns are a change in the language already in the repo.
1. Intent + mode
Read for the outcome, not the literal words. Name what would prove this works, then pick a mode:
| Mode | When |
|---|---|
| Continue | Follow-up refining open work — default when the thread has unfinished work |
| Build | New feature or vertical slice |
| Fix | Broken or unexpected behavior |
| Decide | Architectural fork; plan or one decisive question |
- Follow the thread. Turn N usually steers work in progress. Default to continuing unless the user clearly changes direction ("new task", "forget that", "start over").
- Watch for the X-Y problem. They ask for Y because they think it solves X — reconcile when Y is awkward.
- Don't re-ask answered constraints. Proceed and state assumptions inline.
2. Two speeds
Spend high effort on investigation and a stronger check. A local change finishes in one read-edit-test cycle.
| Speed | When | Do |
|---|---|---|
| Fast (default) | One symbol, a known bug, a small feature in one module | Search the symbol, its callers, and its test in parallel. Smallest diff that matches the file. Run the narrowest check. Stop when it passes. |
| High | New behavior across layers; bug with no line yet; schema, auth, or public API; an idiom absent from the repo; user asked for a real pass | Repro or acceptance sentence, failure modes, product slice when the surface is user-visible, full handoff |
Product slice (screen, endpoint, CLI behavior, multi-layer): before the first edit, one sentence of acceptance — "The user can X and see Y." That sentence is the slice until it is true. Loop: § Build the app. A function or bugfix skips that essay.
3. Confusion weight
Default: infer, state the assumption in one line, act. Ask only when weight is high. Details: clarify-first.
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.
- 26d ago Changed · -2 lines · +78 tokens per session 7843184c7ae9
- 1mo ago First seen · 137 lines · 1,777 tokens per session scan A 753b8b917a01
composer-core is a cursor rule published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 27d ago), licensed MIT. It adds 1,855 tokens to every session, about $0.0074 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
web
Web build conventions (separate from native and RN JS).
data-fetching
Data fetching patterns with TanStack Query, Server Components, and Supabase.
components
Component patterns and UI conventions.
git
Git workflow and commit conventions.
approved-plan-execution
Guard execution of an approved plan or burndown: forbid reward hacking and feature deletion; require checkpoints, context discipline, safe terminal use, and fresh verification. Applies to approved plan-.md, complete-everything, and burndown-full runs, whatever model runs them.
verification-before-completion
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.