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/refactornpx skills add OZmasterAI/Torus-Framework --skill refactorgit 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 | $0.00000 | $0.01139 |
| Opus 5 | $0.00000 | $0.00570 |
| Sonnet 5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
refactor 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refactor — Safe, Incremental Code Refactoring
When to use
When the user says "refactor", "extract", "rename", "simplify", "dead code", "cleanup", "restructure", or wants to reorganize code without changing behavior.
Complements /fix (behavior changes) and /review (analysis only) by performing structural improvements while preserving correctness.
Steps
1. MEMORY CHECK
search_knowledge("refactor")— find prior refactoring attempts and lessons learnedsearch_knowledge("[target file or module]")— check for known issues in the areaquery_fix_history("[target area]")— check if past refactors caused regressions- If prior refactoring caused problems, present the history and adjust approach
2. SCOPE
Clarify the refactoring type and boundaries with the user:
Refactoring types:
- Extract function — Pull a block of code into a named function
- Extract constant — Replace magic numbers/strings with named constants
- Rename symbol — Rename a function, variable, class, or module across the codebase
- Simplify logic — Reduce complexity (flatten nesting, simplify conditionals, remove duplication)
- Dead code removal — Remove unreachable or unused code
- Move/reorganize — Relocate code to a more appropriate file or module
Define boundaries:
- Single file, module, or entire codebase?
- Which functions/classes are in scope?
- Are tests in scope for refactoring too?
If the scope is unclear, ask the user before proceeding.
3. IMPACT ANALYSIS
Before touching any code, assess the blast radius:
- Grep all usages of the target symbol/code pattern
- Count affected files — show the user exactly what will change
- Check for dynamic references — string-based lookups, reflection, config files, templates
- Check for public API exposure — will external consumers be affected?
- Map dependencies — what imports/calls the target? What does it import/call?
Present the impact summary to the user:
Refactoring: [description]
Affected files: N
- file_a.py:L10 — definition
- file_b.py:L25, L40 — usage
- test_file.py:L15 — test reference
Dynamic references: [none found / list them]
Public API impact: [none / description]
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 · 109 lines · 0 tokens per session scan A d9a757c0edde
refactor is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,139 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…