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 oreum-ai/smartstack --skill refactorgit clone --depth 1 https://github.com/oreum-ai/smartstackWrote 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/oreum-ai/smartstack/refactor)<a href="https://agentmods.dev/skills/oreum-ai/smartstack/refactor"><img src="https://agentmods.dev/badge/skills/oreum-ai/smartstack/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/oreum-ai/smartstack/refactor"><img src="https://agentmods.dev/badge/skills/oreum-ai/smartstack/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 | $0.00000 | $0.00371 |
| Opus 5.5 | $0.00000 | $0.00148 |
| Sonnet 5.5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
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 2mo 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
Skill: Refactor
When to use
When code works but is hard to read, duplicated, or fragile — and you want to improve its structure without changing behavior. Not for features; for making existing code cleaner and safer to change.
The golden rule
Refactoring never changes behavior. If behavior should change, that's a feature/fix — do it separately, so each diff is either "same behavior, cleaner" or "new behavior," never both.
Procedure
- Protect first. Ensure the code is covered by tests. If it isn't and it's risky, use
test-writerto add coverage BEFORE refactoring — the tests prove you didn't change behavior. - One transformation at a time. Rename, extract a function, remove duplication, simplify a conditional — each as its own small step. Run tests/lint after each step.
- Keep the diff focused. Don't reformat unrelated lines; it hides the real change.
- Follow existing patterns. Move shared logic into the right home rather than copy-pasting.
- Don't break the public shape. Keep function signatures / API contracts stable unless the task allows changing them.
- Verify. All tests green; lint/build clean; behavior identical.
Good refactor targets
- Duplicate fetches that should share a cached value.
- Repeated validation/guard logic that could be one helper.
- Long functions mixing data, logic, and presentation.
- Dead code, unclear names, deep nesting.
Checklist
- Covered by tests before starting.
- Behavior unchanged (tests still green, same outputs).
- One transformation per step, verified each time.
- Follows repo patterns; diff focused; quality gate clean.
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.
- 2mo ago First seen · 32 lines · 0 tokens per session scan A 9d1719b4d97e
refactor is a skill published in the GitHub repository oreum-ai/smartstack (6 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 371 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…