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 skills/ozmasterai/torus-framework/learnnpx skills add OZmasterAI/Torus-Framework --skill learngit clone --depth 1 https://github.com/OZmasterAI/Torus-FrameworkWhat 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 | $0.00015 | $0.01486 |
| Opus 5 | $0.00008 | $0.00743 |
| Sonnet 5 | $0.00003 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00149 |
Grade A, and why
learn 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 2d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn — Learn from External Sources and Integrate Knowledge
When to use
When the user says "learn about", "teach me", "integrate this", "read this article", "what can we adopt from", or provides a URL/topic they want absorbed into the framework's institutional knowledge.
Invocation Examples
/learn https://docs.example.com/feature— learn from a URL/learn topic: "structured concurrency in Python"— research a topic/learn "how does X handle Y?"— answer a question and remember the findings/learn --apply topic— learn AND propose code changes if improvements are found
Steps
1. GATHER — Collect raw material
Accept one of three input forms:
- URL:
WebFetch(url)to retrieve the page content directly - Topic/Question:
WebSearch("[topic] best practices site:docs OR github OR arxiv")(2-3 targeted queries), thenWebFetchthe top 2-3 results - Both: If a URL is given alongside a question, fetch the URL first, then search for complementary context
During gather, also pull related memory:
search_knowledge("[topic]", top_k=20)to surface what we already know- If memory relevance > 0.5 for several results, present existing knowledge and ask the user if external research is still needed before fetching
2. ANALYZE — Extract what matters for our framework
From the raw fetched content, identify:
- Key patterns: Architectural patterns, design decisions, algorithms
- Techniques: Implementation techniques directly applicable to our codebase
- Best practices: Conventions, rules of thumb, anti-patterns to avoid
- APIs / interfaces: New tools, libraries, or protocols worth knowing
- Limits / caveats: Where the technique breaks down or doesn't apply
Focus the analysis on relevance to the torus-framework: gates, hooks, memory system, agent orchestration, skills, and the CLAUDE.md behavioral rules.
3. CROSS-REFERENCE — Check against existing knowledge
search_knowledge("[each key pattern found]", mode="all")— find overlapping memories- For any high-relevance hit (> 0.4):
get_memory(id)to read the full entry - Identify:
- Confirms: Finding matches what we already knew (note convergence, no re-save needed)
- Extends: Finding adds depth to existing knowledge (save as extension)
- Contradicts: Finding conflicts with existing memory (flag to user, do NOT silently overwrite)
- New: No related memory — save as fresh learning
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.
- 2d ago First seen · 137 lines · 15 tokens per session scan A 97cd1dac78b1
learn is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,486 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…