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-senior-practices)<a href="https://agentmods.dev/rules/madebyaris/cursor-composer-rules/composer-senior-practices"><img src="https://agentmods.dev/badge/rules/madebyaris/cursor-composer-rules/composer-senior-practices.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00516 |
| Opus 5 | $0.00016 | $0.00258 |
| Sonnet 5 | $0.00007 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
composer-senior-practices 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 7d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composer senior practices
Load the senior-practices skill when you need current, version-matched guidance. Training data is a hypothesis until anchored to this repo's versions and T1 sources — not a substitute for primary docs.
When to use
- Unfamiliar framework, library, or language feature in the repo.
- User asks for "best practice", "modern approach", or "how should we…"
- Upgrade, migration, or new pattern introduction.
- Architecture or code review where recommendations need citations.
- Style governance decision: is local style wrong enough to improve? (see composer-coding-excellence § Style governance)
When not to use
- Trivial edits where the file's existing pattern is clear.
- Pure codebase archaeology (use Explore subagent / grep instead).
- Deep multi-vendor research (use composer-deep-research / deep-research skill).
Source tiers
| Tier | Examples | Use for |
|---|---|---|
| T1 — Primary | Official docs, RFCs, release notes, security advisories | Defaults, APIs, deprecations |
| T2 — Maintainer / platform | Framework team blogs, platform engineering guides (version-matched) | Patterns endorsed by platform owners |
| T3 — Corroborated senior | Widely cited talks/posts only when aligned with T1/T2 or reproducible | Tradeoffs, operational wisdom |
| Reject | Random tutorials, outdated Stack Overflow, unversioned "best practices" | Do not cite as authority |
Contract with style governance
Recommendations must reconcile with this repo: existing libs, ADRs, lint config, and composer-coding-excellence minimal-diff rules.
- Apply now — safe within the current task scope.
- Follow-up plan — style or tech-debt slice; do not drive-by refactor.
Never mass-fix unrelated modules based on external guidance alone.
See reference.md for the compact checklist.
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.
- 7d ago First seen · 43 lines · 33 tokens per session scan A b3ea87d51ee8
composer-senior-practices is a cursor rule published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 19d ago), licensed MIT. It adds 33 tokens to every session and 516 once invoked, about $0.0002 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.
Other cursor rules, from other repositories
propose-test-cases
Propose comprehensive test cases for PR changes.
detect-code-smells
Detect code smells and anti-patterns in PR changes.
suggest-improvements
Provide actionable improvement suggestions for PR changes.
include-specs
Use specs/spec-index.md to decide which spec(s) apply to the current task. Only consult/include the spec(s) referenced there that are relevant to the prompt at hand. Specs are the source of truth for scope and acceptance criteria.
update-specs
After implementation has finished, always review if the specs need to be updated, so they will not lag behind (specs will be used for any subsequent work). Use specs/spec-index.md to decide which spec(s) apply to the current task and should be updated.
ask-first
Before starting work new work, especially after a first prompt, always prefer asking to assuming. If uncertain about anything especially user intent or architecture choices, ask for clarifications first.