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/madebyaris/cursor-composer-rulesWrote 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-coding-excellence)<a href="https://agentmods.dev/rules/madebyaris/cursor-composer-rules/composer-coding-excellence"><img src="https://agentmods.dev/badge/rules/madebyaris/cursor-composer-rules/composer-coding-excellence/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-coding-excellence"><img src="https://agentmods.dev/badge/rules/madebyaris/cursor-composer-rules/composer-coding-excellence.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 | $0.00030 | $0.01734 |
| Opus 5.5 | $0.00012 | $0.00694 |
| Sonnet 5.5 | $0.00006 | $0.00347 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
composer-coding-excellence 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 1mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composer coding excellence
Use whenever you are writing or modifying source, tests, types, or build files. The goal is craftsmanship: changes that look like they were written by the person who wrote the surrounding file, in that file's language.
The editing mindset
You are a careful surgeon, not an enthusiastic remodeler.
- Read the file end-to-end (or at least the function plus its callers and tests) before editing.
- Mirror the file's style: naming, imports, error handling, type rigor, docstring tone.
- Make the smallest diff that achieves the goal. Unrelated improvements are a separate task.
- Run the narrowest check that can fail (composer-verification). Widen only when the change is cross-cutting or user-visible.
- Re-read your diff as if reviewing someone else's PR before submitting.
Convention matching is not optional
The codebase's existing patterns are the default. Deviate only with a stated reason.
- If the file uses
camelCase, don't introducesnake_case. - If errors are returned as values, don't throw exceptions.
- If imports are grouped, group yours.
- If functions are pure, keep yours pure.
- If the project tests with framework X, don't introduce framework Y.
- If the project has a logger, use it — don't
console.log.
When you must break convention, say so explicitly in the change description.
Language of the file
The language already in the file is the dialect. Errors, null, async, ownership, tests, and formatting follow that file and the repo's toolchain.
- Match how this repo returns errors, handles absence, and waits on I/O. Importing an idiom from another language is a second style.
- Tests use the framework and naming already in the tree. Extend the test that covers this behavior.
- Format with the repo's formatter. Leave unrelated lines alone.
- If the idiom is not in the repo, one primary lookup via composer-senior-practices, then write it. Do not invent syntax, APIs, or compiler flags.
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.
- 1mo ago Changed · +9 lines · +9 tokens per session deaaa029fd37
- 1mo ago First seen · 137 lines · 21 tokens per session scan A b925bbd49a1c
composer-coding-excellence is a cursor rule published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,734 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
data-fetching
Data fetching patterns with TanStack Query, Server Components, and Supabase.
web
Web build conventions (separate from native and RN JS).
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.