senior-practices

senior-practices is a skill for Cursor from madebyaris/cursor-composer-rules. It costs 59 tokens per session (957 once invoked), scanned A, original, MIT.

A guide for checking coding and framework practices against the versions and official documentation used in a project.

In plain words
What is it for?
Reviewing best practices, checking for deprecated or discouraged approaches, and separating recommendations that can be applied now from follow-up work.
Why use it?
It helps avoid relying on outdated advice when working with unfamiliar tools, upgrades, migrations, or architecture decisions.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Good fit Reviewing best practices, checking for deprecated or discouraged approaches, and separating recommendations that can be applied now from follow-up work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/madebyaris/cursor-composer-rules/senior-practices
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.

Any agent
npx skills add madebyaris/cursor-composer-rules --skill senior-practices
Clone the repo
git clone --depth 1 https://github.com/madebyaris/cursor-composer-rules

Made for: Cursor.

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 senior-practices

README.md
[![agentmods](https://agentmods.dev/badge/skills/madebyaris/cursor-composer-rules/senior-practices/github.svg)](https://agentmods.dev/skills/madebyaris/cursor-composer-rules/senior-practices)
Your own site
<a href="https://agentmods.dev/skills/madebyaris/cursor-composer-rules/senior-practices"><img src="https://agentmods.dev/badge/skills/madebyaris/cursor-composer-rules/senior-practices/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.

agentmods 80×15 button for senior-practices

Your own site · 80×15
<a href="https://agentmods.dev/skills/madebyaris/cursor-composer-rules/senior-practices"><img src="https://agentmods.dev/badge/skills/madebyaris/cursor-composer-rules/senior-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 957 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.00957
Opus 5.5 $0.00024 $0.00383
Sonnet 5.5 $0.00012 $0.00191
Haiku 4.5 $0.00006 $0.00096

Measured 2mo ago against content hash 5b17a4bfecb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 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.

.cursor/skills/senior-practices/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior practices skill

Companion to .cursor/rules/composer-senior-practices.mdc. Load when external, current guidance is needed — not when matching an obvious local pattern suffices.

For multi-vendor audits or contradictory literature, pair with deep-research. For applying findings without scope creep, follow composer-coding-excellence § Style governance.

See reference.md for compact repeatable checklists.

Operating stance

Training data is a hypothesis until anchored to this repo's versions and T1 sources. Prefer falsification: check deprecations, breaking changes, and "do not use" guidance before recommending a pattern. Recollection without a primary source stays [H] until inspected.

Do not imitate private chain-of-thought. Make the work inspectable: version inventory, source list, reconciled recommendations, and apply-now vs follow-up split.

Phase A — Inventory (this repo)

  1. Read manifests: package.json, go.mod, Cargo.toml, pyproject.toml, Gemfile, etc.
  2. Record exact versions of the framework, runtime, and relevant libraries.
  3. Note existing project standards: eslint/prettier, ADRs, README, CI config.
  4. Scan how similar problems are already solved in this codebase (2–3 examples).

If versions cannot be determined, say so and label recommendations [H] until anchored.

Phase B — Anchor (T1 primary)

For each decision point:

  1. Open official docs keyed to the pinned version (not "latest" unless the repo tracks latest).
  2. Read release notes / migration guides for the version span in use.
  3. Check security advisories when the change touches auth, crypto, input, or dependencies.

Draft a short coverage note: what T1 says, what is deprecated, what the repo currently does.

Phase C — Corroborate (T2/T3, sparingly)

Add T2/T3 sources only when T1 is silent on the specific decision:

  • Platform owner guides (Vercel, Cloudflare, etc.) matched to deployment target.
  • Maintainer conference talks or engineering blogs when they align with T1 or include reproducible examples.

Read the full file on GitHub · 107 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 107 lines · 59 tokens per session scan A 5b17a4bfecb7

Subscribe to this mod's changes

senior-practices is a skill published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 957 once invoked, about $0.0002 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.

Related

senior-practices compared with skills from other repositories

senior-practices next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
senior-practicesmadebyaris/cursor-composer-rulesSkill31mo agoMITA59Cursor
enhance-web-landingkensaurus/cursor-kenjiSkill91mo agoMITA59Claude Code
audit-payment-systemkensaurus/cursor-kenjiSkill91mo agoMITA66Claude Code
enhance-web-uxkensaurus/cursor-kenjiSkill91mo agoMITA68Claude Code
enhance-web-web3dkensaurus/cursor-kenjiSkill91mo agoMITA69Claude Code
mobile-rn-screenkensaurus/cursor-kenjiSkill91mo agoMITA54Claude Code
audit-backend-architecturekensaurus/cursor-kenjiSkill91mo agoMITA58Claude Code