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/soulcodex/agentic/refactornpx skills add soulcodex/agentic --skill refactorgit clone --depth 1 https://github.com/soulcodex/agenticWhat 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 | $0.00046 | $0.00526 |
| Opus 5 | $0.00023 | $0.00263 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00053 |
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 2d 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
Refactor Skill
Improve the code structure without changing external behavior.
Step 1 — Understand the Goal
Ask or infer:
- What is wrong with the current code? (too long, duplicated, wrong layer, hard to test)
- What is the desired outcome? (extracted function, renamed variable, moved to correct layer)
- Are there tests in place? (if not, write characterization tests before refactoring)
Step 2 — Establish a Safety Net
Before changing anything, verify tests exist that cover the code being refactored. If tests are missing, write characterization tests first:
- A characterization test captures current behavior (even if the behavior is wrong).
- It prevents accidental behavior changes during refactoring.
Step 3 — Apply Refactoring in Small Steps
Work in small, safe increments. After each step, verify tests still pass:
Common refactoring moves:
- Extract function/method: identify a coherent chunk of logic with a clear purpose.
- Rename: choose a name that accurately describes the thing at the current abstraction level.
- Move to correct layer: domain logic in a controller → move to use case or domain service.
- Replace conditional with polymorphism: complex switch/if chains on type → strategy pattern.
- Introduce value object: raw primitive used to represent a domain concept → wrap it.
- Remove duplication: extract shared logic to a shared function; do not abstract prematurely.
Step 4 — Verify Behavior is Unchanged
After refactoring:
- All tests pass.
- The public API (exported signatures) is unchanged.
- No new dependencies introduced.
Step 5 — Summarize
## Refactor Summary
**What changed**: [List of moves applied]
**Why**: [The design problem that was addressed]
**Tests**: [Pass / added N new characterization tests]
**Breaking changes**: None (internal only)
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.
- 2d ago First seen · 68 lines · 46 tokens per session scan A 1e8e7a9ce836
refactor is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 526 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
improve-codebase-architecture
Use when surfacing architectural friction inside a single EVOKORE bounded context and proposing deepening refactors (shallow modules, leaky seams, low locality) that turn shallow modules into deep ones — informed by ADR-0005 bounded contexts and the project's domain language.
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
survey-design
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).
localization-design
Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
design-debt-audit
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).