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 1aifanatic/super-computer --skill refactorgit clone --depth 1 https://github.com/1aifanatic/super-computerWrote 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/1aifanatic/super-computer/refactor)<a href="https://agentmods.dev/skills/1aifanatic/super-computer/refactor"><img src="https://agentmods.dev/badge/skills/1aifanatic/super-computer/refactor/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/1aifanatic/super-computer/refactor"><img src="https://agentmods.dev/badge/skills/1aifanatic/super-computer/refactor.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 | $0.00039 | $0.00459 |
| Opus 5.5 | $0.00016 | $0.00184 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago First seen · 36 lines · 39 tokens per session scan A 29432c001131
refactor is a skill published in the GitHub repository 1aifanatic/super-computer (1 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 459 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
flaremo-memory
A shared memory ledger for coding agents. It defines how agents check project rules, record facts during work, and save a handoff report at the end.
cloudflare-workers-debugging
Use when wrangler deploys silently fail or produce wrong artifacts, secrets upload as empty strings, custom domain DNS is not resolving, route assignment broke after rename, observability/tail logs are needed, D1/KV/R2 bindings are missing, OAuth scope errors block a command, cookies on a redirect are not attaching…
tanstack-devtools
Centralized, extensible devtools panel for TanStack libraries with a plugin architecture.
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.