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/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/skills/madebyaris/cursor-composer-rules/deep-research"><img src="https://agentmods.dev/badge/skills/madebyaris/cursor-composer-rules/deep-research.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 | $0.00061 | $0.01171 |
| Opus 5.5 | $0.00024 | $0.00468 |
| Sonnet 5.5 | $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 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.
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.
- 2mo 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 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,171 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.
deep-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deep-researchmadebyaris/cursor-composer-rules | Skill | 3 | 1mo ago | MIT | A | 61 | Cursor |
| enhance-web-landingkensaurus/cursor-kenji | Skill | 9 | 1mo ago | MIT | A | 59 | Claude Code |
| audit-payment-systemkensaurus/cursor-kenji | Skill | 9 | 1mo ago | MIT | A | 66 | Claude Code |
| enhance-web-uxkensaurus/cursor-kenji | Skill | 9 | 1mo ago | MIT | A | 68 | Claude Code |
| enhance-web-web3dkensaurus/cursor-kenji | Skill | 9 | 1mo ago | MIT | A | 69 | Claude Code |
| mobile-rn-screenkensaurus/cursor-kenji | Skill | 9 | 1mo ago | MIT | A | 54 | Claude Code |
| audit-backend-architecturekensaurus/cursor-kenji | Skill | 9 | 1mo ago | MIT | A | 58 | Claude Code |