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 saski/arnesto --skill refactoringgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/refactoring)<a href="https://agentmods.dev/skills/saski/arnesto/refactoring"><img src="https://agentmods.dev/badge/skills/saski/arnesto/refactoring/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/saski/arnesto/refactoring"><img src="https://agentmods.dev/badge/skills/saski/arnesto/refactoring.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 | $0.00027 | $0.00619 |
| Opus 5.5 | $0.00011 | $0.00248 |
| Sonnet 5.5 | $0.00005 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
refactoring 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.
This is a copy
100% identical to refactoring — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Production Code
STARTER_CHARACTER = 🟣
When starting, announce: "🟣 Using REFACTORING skill".
Work autonomously as much as possible. Start with the simplest thing or file and proceed to the more complex ones.
Stages
- Prep
- Main Refactoring
- Final Evaluation
- Summary
Test Code Policy
Do not change test code during refactoring, except:
- Renames that follow production code renames (imports, function calls)
- Import path updates if something moved
Never change test assertions, test data, or test logic.
1. Prep
- Determine scope: use specified files, or identify related files (imports, shared functionality), or ask user
- Add files in scope to todo list
- Find or create ./test.sh, verify all tests pass
- Remove comments from files in scope (commit per file)
2. Main Refactoring
Code Style
Prefer self-explanatory, readable code over comments.
- Use functional helper methods for clarity
- Remove dead code
- Extract paragraphs into methods
- Use better variable names
- Remove unused imports
- Remove unhelpful local variables
- Look for opportunities to simplify
- Use domain language - name things for what they ARE, not how they're implemented
- Keep consistent abstraction levels within methods
Process
For each refactor:
- Ensure all tests pass
- Choose and perform the simplest possible refactoring (one at a time)
- Ensure all tests pass after the change
- Commit each successful refactor with the message format: "- r " (the message must include the "- r" prefix) Prefer small granular commits. If applying the same refactoring pattern to multiple locations, change one location at a time and commit each separately.
- Provide a status update after each refactor
3. Final Evaluation
When you see no more obvious refactoring opportunities, say "🔍 Entering final evaluation."
Shift focus: you've been implementing. Now become a critic. Your job is to find problems, not produce code.
Re-read Code Style guidelines. Look at each file in scope. Consider blind spots - what improvements haven't we even considered that would make the code better, easier, more maintainable?
What ships with it
2 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 · 85 lines · 27 tokens per session scan A 4dc334cb64da
refactoring is a skill published in the GitHub repository saski/arnesto (6 stars, last pushed 5d ago), licensed Unlicense. It adds 27 tokens to every session and 619 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to refactoring, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
wicked-garden-qe-flaky-test-hunter
Flake detection + root-cause specialist. Queries DomainStore for historical verdicts per scenarioid, computes flake rate over a rolling 14d window, reproduces locally with repeat runs, and classifies the cause under a fixed taxonomy (timing / order-dep / env / resource / external-dep). Never proposes "add retry" as a…
systematic-debugging
Reproduce failures, isolate root cause with evidence, and fix them through a regression test.
testing
Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
mcore-testing
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.