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 agentmods add skills/sylorei/claude-godmode/refactornpx skills add SyloRei/claude-godmode --skill refactorgit clone --depth 1 https://github.com/SyloRei/claude-godmodeWrote 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/sylorei/claude-godmode/refactor)<a href="https://agentmods.dev/skills/sylorei/claude-godmode/refactor"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/refactor.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01246 |
| Opus 5 | $0.00018 | $0.00623 |
| Sonnet 5 | $0.00007 | $0.00249 |
| Haiku 4.5 | $0.00004 | $0.00125 |
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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Refactoring
Improve code structure without changing behavior. Every step verified by tests, with quality gates passing before and after each change.
Auto Mode
When ## Auto Mode Active is present in context: do not pause for confirmation. Plan the steps using reasonable defaults, surface the plan and assumptions inline, then execute step by step with per-step quality gates. When the refactor's scope or target is genuinely ambiguous — what to restructure into what — ask, following the shared recommendation convention (godmode:recommend-convention) in rules/godmode-recommend.md: lead with your best-inferred answer to override, not a blank prompt (e.g. "I'll extract X into Y unless you'd scope the boundary differently"), then let the user redirect. Treat user course-corrections as normal input.
The Job
- Verify baseline
- Plan steps
- Execute one step at a time with test verification
- Report results
Process
1. BASELINE
- Run ALL quality gates (from
config/quality-gates.txt). They must pass. - If not: fix quality issues first (separate commit).
- Note current test count and coverage.
2. IDENTIFY
- What specifically needs improving and WHY
- Is this refactoring or a behavior change? (If behavior → wrong skill, use normal workflow)
- Scope: list exactly which files/functions are affected
3. PLAN
- Break into steps, each independently committable
- Order: safest/simplest first, riskiest last
- Each step leaves the code in a working state
4. EXECUTE (repeat per step)
a. Apply one refactoring
b. Run quality gates
c. If GREEN → commit: "refactor: [what was done]"
d. If RED → revert immediately, try smaller step
5. VERIFY
- Run full quality gates
- Compare test count (same or higher, never lower)
- Compare coverage (same or higher)
- Confirm: no behavior changed
Common Refactorings
| Refactoring | When to use |
|---|---|
| Extract function | >40 lines, mixed responsibilities |
| Rename | Name doesn't describe purpose |
| Inline | Abstraction adds complexity without value |
| Move | Code in wrong module/file |
| Split file | >300 lines or mixed responsibilities |
| Simplify conditional | Nested if/else, complex booleans |
| Replace magic values | Hardcoded numbers/strings |
| Improve types | any, loose types where precise ones exist |
What ships with it
1 file 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.
- 5d ago First seen · 138 lines · 37 tokens per session scan A f5b32faeea37
refactor is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,246 once invoked, about $0.0002 per session on Opus 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
discover
Use when a contextualizer's reference coverage needs to grow against its registered sources — a fresh contextualizer's first pass, quarterly upkeep, or whenever the catalog is lagging what users are asking — to propose new reference files.
refresh
Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.
review
Use when DISCOVER or REFRESH has surfaced a proposal staged at -context.proposed/, to inspect it and record sign-off before applying it.
status
Use when picking up a contextualizer after a gap, or checking reference freshness and pending review work at a glance — read-only, safe to run anytime.
new-reference
Use when a single topic is already identified and a full DISCOVER pass would be overkill, to register one new reference in an existing contextualizer.
using-skill-engine
When the user mentions skill-engine or "the engine" without naming a specific workflow, or wants first-run setup. Inspects .claude/skills/-context/ install state (and any pending -context.proposed/ proposals) across all three install levels, then dispatches to engine-bootstrap when no contextualizer exists, to…