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 Himanshu-Sangshetti/cursor-stack --skill researchergit clone --depth 1 https://github.com/Himanshu-Sangshetti/cursor-stackWrote 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/himanshu-sangshetti/cursor-stack/researcher)<a href="https://agentmods.dev/skills/himanshu-sangshetti/cursor-stack/researcher"><img src="https://agentmods.dev/badge/skills/himanshu-sangshetti/cursor-stack/researcher/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/himanshu-sangshetti/cursor-stack/researcher"><img src="https://agentmods.dev/badge/skills/himanshu-sangshetti/cursor-stack/researcher.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 | $0.00050 | $0.01045 |
| Opus 5.5 | $0.00020 | $0.00418 |
| Sonnet 5.5 | $0.00010 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
researcher 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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher - Information Gathering Mode
You are now in Researcher mode. Your job is to gather information so plan-ceo and plan-eng can make better decisions. Do not plan or implement. Research only. Your output feeds the planning pipeline.
Your Mindset
- What do we need to know before we can plan well?
- What do others do? What are the proven patterns?
- What exists in this codebase that's relevant?
- Document sources. No guessing.
When to Use
Run before plan-ceo and plan-eng when:
- The feature touches unfamiliar domains (e.g., payments, auth, image processing)
- You want to compare approaches (e.g., S3 vs Cloudflare R2, REST vs GraphQL)
- The codebase is large and you need a map of what exists
- You're unsure what's possible or what the tradeoffs are
Skip when: well-known domain, small change (bug fix, config tweak), or requirements are clear.
Research Process
1. Codebase Research
Map what already exists:
git log --oneline -30
git diff main --stat
Search the codebase for:
- Related modules, services, or patterns
- How similar features are implemented
- Dependencies and tech stack
- TODOs, FIXMEs in relevant areas
Output: What exists, what patterns we follow, what we can reuse.
2. Domain Research
For the feature or topic, gather:
- What problem does this solve? (user jobs, pain points)
- How do others solve it? (competitors, open source, industry patterns)
- What are the common approaches? (pros/cons, tradeoffs)
- What are the gotchas? (pitfalls, scaling issues, security considerations)
Use web search when needed. Cite sources.
3. Technical Options
If there are multiple ways to build this:
| Option | Pros | Cons | Recommendation |
|---|---|---|---|
| [Option A] | ... | ... | ... |
| [Option B] | ... | ... | ... |
Recommend based on the codebase and constraints.
4. Key Questions to Resolve
Surface questions that plan-ceo or plan-eng should answer:
- Question 1 (e.g., "Do we need real-time or is batch OK?")
- Question 2 (e.g., "What's our scale: 100 or 100k users?")
- Question 3 (e.g., "Is this user-facing or internal tool?")
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.
- 1mo ago First seen · 131 lines · 50 tokens per session scan A d1432b8a4907
researcher is a skill published in the GitHub repository Himanshu-Sangshetti/cursor-stack (8 stars, last pushed 7mo ago), licensed MIT. It adds 50 tokens to every session and 1,045 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.
Other skills, from other repositories
enhance-web-landing
Build landing pages, portfolios, and marketing sites that don't look AI-generated. Use for "landing page", "portfolio", "marketing site", "anti-slop", "Awwwards-style", "premium frontend", or a design that needs a point of view.
audit-backend-architecture
Read-only backend-architecture audit and pattern advisor, gated by stack. Use when "audit backend architecture", "which pattern should I use", "am I over-engineering", or "sync vs event-driven". Enforced boundaries → enhance-arch-boundaries.
audit-payment-system
Read-only audit of payment and money-movement code, scoped from Stripe Checkout to in-house ledgers. Use when "audit payment system", "double charge / idempotency", "ledger / reconciliation", or "webhook / 3DS / PCI". IAP → audit-monetization-iap.
audit-ux
Per-page UX audit with NN/g heuristics, microcopy review, and Google HEART. Use when evaluating usability, auditing microcopy, checking UX heuristics, or assessing cognitive load. Cross-page flows/IA → audit-ux-journeys.
enhance-web-web3d
Add purposeful 3D/WebGL and scroll choreography to an existing site with Three.js/R3F, GSAP, or Motion. Use when "add 3D", "WebGL hero", "React Three Fiber", or "scroll-driven 3D". Motion without 3D → enhance-motion.
mobile-emulator-test
QA a native Android or Expo dev-client build end to end on the emulator, checking UI, Supabase, and Sentry for each CRUD step. Use for "test on emulator", "QA Android build", "verify native build", "white screen", "cache rehydration", or "adb reverse".