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.
npx skills add madebyaris/cursor-composer-rules --skill deep-researchgit 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/skills/madebyaris/cursor-composer-rules/deep-research)<a href="https://agentmods.dev/skills/madebyaris/cursor-composer-rules/deep-research"><img src="https://agentmods.dev/badge/skills/madebyaris/cursor-composer-rules/deep-research.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 | $0.00061 | $0.01171 |
| Opus 5 | $0.00030 | $0.00585 |
| Sonnet 5 | $0.00012 | $0.00234 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
deep-research 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep research skill
Companion to .cursor/rules/composer-deep-research.mdc; load this when retrieval depth exceeds quick-rule ergonomics (more than a few independent sources, contradictory docs, benchmarking, compliance or security narratives).
For wide codebase surveys, pair this skill's claim ledger with the built-in Explore subagent or composer-orchestration — keep raw search noise out of the parent thread.
See reference.md for compact repeatable checklists.
Operating stance
Assume initial answers are hypotheses until corroborated — including training-data familiarity. Prioritise falsification (finding counter-evidence or version skew) ahead of reinforcing comfortable narratives.
Do not imitate private chain-of-thought. Make the research inspectable through compact artifacts: a plan, a claim ledger, a contradiction log, and a confidence-bearing conclusion. Close out so the parent can restate a standalone conclusion with confidence tiers.
Phase A — Clarify investigative goal
Produce internally (surface only if ambiguity blocks progress):
| Facet | Pin down |
|---|---|
| Question type | Comparative, diagnostic, explanatory, procedural, forecasting (each steers retrieval) |
| Decision utility | Actionable takeaway vs exploratory survey |
| Time/version window | Freeze target stack release or cutoff date explicitly |
| Non-goals | Exclusions narrowing scope creep |
| Success signal | Acceptance evidence that would persuade a sceptical reviewer |
Avoid expanding scope preemptively unless the user requests a landscape survey.
When the task is deep or high-stakes, surface a brief research plan before the final synthesis:
Research plan:
- Scope:
- Primary anchors:
- Counter-evidence pass:
- Stop condition:
Phase B — Retrieval passes (iterate two to four times typical)
Structure passes deliberately.
Pass 1 — Primary anchors
- Official docs and readmes keyed to version.
- Specs, RFCs, or issue trackers for definitive semantics.
- Security advisories, changelogs, and CVE metadata feeding risk statements.
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.
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 · 154 lines · 61 tokens per session scan A baaec544004f
deep-research is a skill published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 19d ago), licensed MIT. It adds 61 tokens to every session and 1,171 once invoked, about $0.0003 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 skills, from other repositories
Cursor AI Testing Patterns
Effective test automation patterns with Cursor AI IDE including Composer for test suite generation, Cmd+K for inline test edits, Chat for test debugging, codebase-aware test generation, and rules configuration for testing conventions.
ui-design
Create distinctive, production-grade web interfaces with high design quality using Tailwind CSS. Use for building UI components, pages, dashboards, apps, and web applications. Generates crafted, polished code that avoids generic AI aesthetics.
code-review-codex
Final-gate code review via Codex CLI (codex-5.3, xhigh). Finds bugs, security issues, and regressions before commit. No edits — findings report only.
summarizer
Summarize a YouTube video or podcast episode and save the summary as a structured note in NotePlan under '3 Resources/Podcasts, YT/'. Use this skill whenever the user shares a YouTube link and wants it summarized, noted, or saved — or says things like 'summarize this', 'add this to my notes', 'save this podcast'…
noteplan
Read, search, create, and edit NotePlan notes and daily logs directly via the filesystem. Use this skill whenever the user references NotePlan, daily notes, weekly notes, project notes, or wants to check/update their planning. Triggers: 'noteplan', 'daily note', 'today's note', 'weekly note', 'check my notes', 'add to…
yt-transcript
Fetch YouTube video transcripts and load them into context for further processing. Use this skill whenever the user shares a YouTube URL or video ID and wants to work with the video's content — summarizing, extracting insights, answering questions about it, translating, or feeding it into another workflow. Also…