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 OZmasterAI/Torus-Framework --skill researchgit clone --depth 1 https://github.com/OZmasterAI/Torus-FrameworkWrote 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/ozmasterai/torus-framework/research)<a href="https://agentmods.dev/skills/ozmasterai/torus-framework/research"><img src="https://agentmods.dev/badge/skills/ozmasterai/torus-framework/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/ozmasterai/torus-framework/research"><img src="https://agentmods.dev/badge/skills/ozmasterai/torus-framework/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 | $0.00000 | $0.00713 |
| Opus 5.5 | $0.00000 | $0.00285 |
| Sonnet 5.5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
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 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research — Structured Research with Memory Integration
When to use
When the user says "research", "look into", "investigate", "find out about", "what is", or needs to gather information before making a decision.
Depth Tiers
Use --depth <tier> to set research intensity (default: standard):
| Tier | Agents | Hops | Time | Use Case |
|---|---|---|---|---|
| quick | 0 (direct) | 0 | ~30s | Simple factual lookups |
| standard | 2-4 | 1 | 2-5min | General research (default) |
| deep | 4-6 | 2 | 5-10min | Comprehensive investigation |
| exhaustive | 6+ team | 3 | 10-20min | Full academic-level research |
Hop Patterns (for deep/exhaustive)
- entity-expansion: X → related entities → explore each (Company → Products → Competitors)
- temporal: current state → recent changes → historical context → future implications
- conceptual-deepening: overview → details → examples → edge cases → limitations
- causal-chains: observation → immediate cause → root cause → fix options
Steps
- MEMORY CHECK — search_knowledge("[topic]", top_k=50) for existing knowledge on the topic:
- Check what we already know before searching externally
search_knowledge("[topic]", mode="all")for related past observations- If sufficient knowledge exists, present it and ask if deeper research is needed
- SCOPE — Define 3-5 specific research questions:
- Break the broad topic into focused, answerable questions
- Prioritize questions by impact on the user's decision
- Present the research plan to the user for confirmation
- GATHER — Launch sub-agents based on depth tier (quick: direct calls, standard: 2-4, deep: 4-6 with hop patterns, exhaustive: 6+ team with multi-hop):
- Web researcher: WebSearch + WebFetch for online sources (docs, articles, comparisons)
- Codebase explorer: Glob + Grep + Read for relevant local code, patterns, and dependencies
- Memory miner: search_knowledge (mode="all" for observations too) for past decisions and learnings
- Each agent targets specific research questions from Step 2
- SYNTHESIZE — Combine findings into a structured report:
- Key Findings: Direct answers to each research question
- Evidence: Links, code references, and memory entries supporting each finding
- Gaps: Questions that couldn't be fully answered
- Recommendations: Actionable next steps based on findings
- Trade-offs: Pros/cons if comparing options
- SAVE — remember_this() for each significant finding:
- Tag with "type:learning" and relevant area tags
- Save key decisions and their rationale
- Save links to important resources for future reference
- PRESENT — Display formatted report to user:
- Use clear markdown headings and bullet points
- Highlight the most important findings
- End with a clear recommendation or set of options
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 · 49 lines · 0 tokens per session scan A c2272cf5e1de
research is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 713 tokens. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…