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 Aquifer-sea/pattern8 --skill refactorgit clone --depth 1 https://github.com/Aquifer-sea/pattern8Wrote 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/aquifer-sea/pattern8/refactor)<a href="https://agentmods.dev/skills/aquifer-sea/pattern8/refactor"><img src="https://agentmods.dev/badge/skills/aquifer-sea/pattern8/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/aquifer-sea/pattern8/refactor"><img src="https://agentmods.dev/badge/skills/aquifer-sea/pattern8/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 | $0.00024 | $0.00340 |
| Opus 5.5 | $0.00010 | $0.00136 |
| Sonnet 5.5 | $0.00005 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
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
Code Refactor
Constrains the Agent to perform safe code refactoring: guarantee functional equivalence while improving code quality.
Step 1: Inversion (Requirements Alignment)
Before refactoring, you must check every item in assets/checklist.yaml.
Step 2: Generator (Generate Refactoring Plan from Template)
Your output must strictly follow the format in assets/template.yaml.
Must include: refactoring goal, impact analysis, refactoring steps (with diff), behavioral equivalence checklist.
Step 3: Tool Wrapper (Security Fence)
If you need to execute code during refactoring for verification, check references/security.yaml first.
Do not delete tests or remove error handling logic during refactoring.
Step 4: Reviewer (Self-Audit Loop)
Audit your refactoring output against references/guidelines.yaml.
Key checks: is the behavior equivalent? Are public APIs unchanged? Is code complexity reduced?
Roll back and regenerate if non-compliant, up to 3 retries.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 45 lines · 24 tokens per session scan A f466a2b4ad6c
refactor is a skill published in the GitHub repository Aquifer-sea/pattern8 (44 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 340 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
review-stack
Stack review of one or more third-party tools (OXC, TanStack, Vite, cf, Sentry, pnpm, Claude Code...) against current official best practices, or of what a dependency bump brings (bumped): one parallel subagent per tool, verified findings, one consolidated plan in chat. USE WHEN: user runs /review-stack or explicitly…
review
Code and design review of this repo by domain - architecture, ci, code-quality, configuration, performance, security, seo, simplicity, tests, ui: one parallel reviewer subagent per selected domain, verified findings, one consolidated plan in chat with IDs to answer. USE WHEN: user runs /review, optionally with domains…
resolve-fixed-pr-comments
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
review-local-changes
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.
attach-review-to-pr
Add line-specific review comments to pull requests using GitHub CLI API.
critique
Comprehensive multi-perspective review using specialized judges with debate and consensus building.