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/1aifanatic/super-computer/refactornpx skills add 1aifanatic/super-computer --skill refactorgit clone --depth 1 https://github.com/1aifanatic/super-computerWhat 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 | $0.00039 | $0.00459 |
| Opus 5 | $0.00019 | $0.00230 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
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.
What it actually says
Systematic multi-file edits
The danger in a refactor is not the edit, it is the edit you did not know you needed to make. Find the full blast radius before changing anything.
Always, in this order
- Enumerate.
grep -rn "oldName" /workspace— every occurrence, before touching one. - Count.
grep -rc "oldName" /workspaceper file, so you know when you are done. - Classify. Definitions, call sites, imports, strings, comments and tests need different treatment. A blind replace corrupts the ones that are not code.
- Edit with
edit_file, one occurrence at a time with enough surrounding context to be unique. - Verify.
grep -rn "oldName" /workspaceagain. Zero results, or only the ones you deliberately left.
Use edit_file, not write_file
Rewriting a file to change one line bills the whole file as output tokens and risks losing anything you did not carry across. edit_file fails loudly when old_string is not unique, which is a feature: that error is telling you the change is ambiguous and needs more context.
When a change genuinely is uniform across a file, replace_all is correct — but check the count first so you know what you are agreeing to.
Partial-word traps
grep matches substrings. Renaming user will also hit username, userId and superuser. Anchor the pattern:
grep -rnw "user" /workspace
grep -rn "\buser\b" /workspace
The limit you must state
You cannot run the tests, the build, or the type checker. A refactor that looks complete is unverified. When you finish, say so plainly — "renamed 14 occurrences across 6 files; not compiled or tested" — rather than implying the change is known good.
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 · 36 lines · 39 tokens per session scan A 29432c001131
refactor is a skill published in the GitHub repository 1aifanatic/super-computer (2 stars, last pushed 21d ago), licensed MIT. It adds 39 tokens to every session and 459 once invoked, about $0.0002 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
changelog-writer
This skill should be used when the user asks to "add a changelog entry", "write changelog", "audit changelog", "review changelog", "check changelog entries", or is editing docs-mintlify/changelog.mdx. Enforces a consistent, reader-facing voice and cuts implementation trivia.
add-media
This skill should be used when the user asks to "add a movie", "add a vinyl", "add to my collection", "add physical media", "add a Blu-ray", "add a CD", or "bought these records". It handles both movies (via TMDb/Trakt) and music (via Discogs).
media-search
This skill should be used when the user asks to "search for a movie", "find a record on Discogs", "look up a film", "search TMDb", "search Discogs", "what's the TMDb ID for", "what's the Discogs ID for", or wants to look up media metadata before adding it to the collection.
frontend-design-landing-page
Marketing landing page and conversion-focused product page reference. Use this skill when building hero sections, feature grids, pricing pages, testimonials, CTAs, footers, navigation bars, or any public-facing marketing surface. Covers a warm, professional, developer-friendly design language (cream backgrounds…
frontend-design-saas
S-tier SaaS dashboard and product UI reference. Use this skill when building application shells, data tables, settings panels, billing pages, dashboards, auth flows, admin tools, or any internal/customer-facing SaaS product UI. Inspired by Stripe, Linear, Vercel, Airbnb, Notion. Covers neutral-led design tokens…
cloudflare-bundler-apps
Author Cloudflare Worker Bundler-compatible apps that build and preview correctly inside a space. Use this skill whenever you scaffold, modify, or deploy a project that will be built with @cloudflare/worker-bundler (i.e. anything served from /space/:name/preview/:branch/). Covers wrangler config, project layout…