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 agentmods add rules/madebyaris/cursor-composer-rules/composer-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/rules/madebyaris/cursor-composer-rules/composer-deep-research)<a href="https://agentmods.dev/rules/madebyaris/cursor-composer-rules/composer-deep-research"><img src="https://agentmods.dev/badge/rules/madebyaris/cursor-composer-rules/composer-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 | $0.00028 | $0.00756 |
| Opus 5 | $0.00014 | $0.00378 |
| Sonnet 5 | $0.00006 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
composer-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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composer deep research
When the user asks for investigation, comparisons, unfamiliar domains, audits, benchmarks, regulation-style questions, vendor claims, historical timelines, architecture surveys, threat models grounded in citations, etc., shift into research mode. This is an edge tool, not the default build path.
Training data and prior familiarity are hypotheses until T1-anchored. Prefer primaries over recollection.
Expanded playbook: use the skill at .cursor/skills/deep-research/SKILL.md for ladders, contradiction logging, and long-form workflows.
Outcome shape
Produce answers in this order:
- Scoped conclusion framed to the user’s constraints (explicit assumptions).
- What primary sources establish versus what rests on weaker synthesis.
- Conflicts/disagreements between sources—with dates/versions/context.
- Action recommendation tied to assumptions and uncertainties.
- How to verify (commands, dashboards, reproducible benchmarks, authoritative doc sections).
Avoid confident absolutes unless directly supported—flag confidence per claim tier.
Visible research thinking
Do not expose private chain-of-thought or invented <thinking> blocks. Instead, externalize auditable reasoning artifacts:
- Research plan: question, assumptions, source ladder, search angles, stop condition.
- Claim ledger: important claim → source/evidence tier → counter-evidence checked → confidence.
- Decision rationale: short “because” statements tied to evidence, not vibes.
- Residual uncertainty: what would change the conclusion and how to test it.
For quick answers, compress these into 2–4 sentences. For deep research, keep them explicit.
Source ladder (default tiering)
Prefer, in descending trust for engineering facts unless the question is inherently opinion-heavy:
- Specifications, RFCs, official vendor docs keyed to product/version pages.
- Language/runtime/framework official guides and changelog entries—not random tutorials.
- Source repositories tagged releases, SECURITY advisories, CVE records with linked metadata.
- Peer-reviewed/academic/industry-neutral references when factual claims hinge on measurements.
- Secondary blogs/forums/stack answers—explicitly labelled as heuristic or anecdotal corroborating evidence.
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.
- 5d ago First seen · 66 lines · 28 tokens per session scan A 16a6162ab9e4
composer-deep-research is a cursor rule published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 17d ago), licensed MIT. It adds 28 tokens to every session and 756 once invoked, about $0.0001 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
cursorrules
You are an expert in WordPress, PHP, and Gutenberg block development.
golang
Follow effective Go conventions. Use table-driven tests. Handle all errors explicitly. No blank error returns. Use context.Context for cancellation and timeouts. Prefer composition over embedding.
module-01
Follow module 01 conventions. Keep boundaries clean. Use dependency injection. No circular imports. Document public APIs with JSDoc.
module-02
Follow module 02 conventions. Keep boundaries clean. Use dependency injection. No circular imports. Document public APIs with JSDoc.
module-03
Follow module 03 conventions. Keep boundaries clean. Use dependency injection. No circular imports. Document public APIs with JSDoc.
module-04
Follow module 04 conventions. Keep boundaries clean. Use dependency injection. No circular imports. Document public APIs with JSDoc.