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 genai-io/san --skill refactorgit clone --depth 1 https://github.com/genai-io/sanWrote 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/genai-io/san/refactor)<a href="https://agentmods.dev/skills/genai-io/san/refactor"><img src="https://agentmods.dev/badge/skills/genai-io/san/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/genai-io/san/refactor"><img src="https://agentmods.dev/badge/skills/genai-io/san/refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.00651 |
| Opus 5.5 | $0.00034 | $0.00260 |
| Sonnet 5.5 | $0.00017 | $0.00130 |
| Haiku 4.5 | $0.00008 | $0.00065 |
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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor: restructure without changing behavior
A refactor changes the shape of code, never what it does. The one rule that makes it safe: behavior is pinned by tests before you touch anything, and the same tests stay green after. If behavior needs to change, that is not a refactor — stop and treat it as a feature or a fix.
Phase 1: Pin the behavior
Before restructuring, make the current behavior observable and guarded.
- Find the tests that cover the code you intend to move. Run them and confirm they pass. This green run is your baseline — write it down.
- If the code is not covered, add characterization tests first: tests that capture what the code does today (not what it should do), enough to catch a behavior change. Get them green against the current code before you refactor.
- If you cannot get the behavior under test at all, say so and stop — an unguarded refactor is a rewrite in disguise, and you would have no way to know you broke something.
Phase 2: Restructure in small steps
Make one structural move at a time, and keep the tests green between moves.
- Each step is a single transformation — extract a function, rename a symbol, inline a variable, split a file, unify duplicated blocks — not a pile of them.
- Run the tests after each step. If they go red, the last step changed behavior; undo it and make a smaller move.
- Change structure only. No new parameters "while you're in there", no bug fixes,
no renamed behavior. If you spot a bug, note it for a separate
code-reviewpass — do not fix it inside the refactor. - Match the conventions already in the code; a refactor should look like it was always there.
Phase 3: Verify behavior is unchanged
- Run the full test suite. It must be as green as your Phase 1 baseline — same tests passing, none skipped to get there.
- Confirm the public interface callers depend on is unchanged, or if it changed, that every call site was updated in the same pass.
- The diff should contain only structural change. Every hunk traces to the restructuring goal; if a hunk changes behavior, it does not belong here.
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 · 63 lines · 84 tokens per session scan A 103cd98082dc
refactor is a skill published in the GitHub repository genai-io/san (78 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 651 once invoked, about $0.0003 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
code-review
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
review-harness
Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.
scrutiny-validator
Adversarial scrutiny procedure for engineering validation assignments. Runs hard-gate commands, reviews the current implementation and evidence integrity against assigned contracts, can use feature-reviewer lanes, and returns per-target verdicts.
ahk-review
Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis. No tasks created, no harness tracking.
pi-parity-review
Adversarially verify that a ported change is faithful to the original pi implementation (TS source + published npm build). Use after porting upstream pi changes, or standalone on any area of this repo ("is X faithful to pi?").