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/nklisch/claude-code-modes/structural-refactornpx skills add nklisch/claude-code-modes --skill structural-refactorgit clone --depth 1 https://github.com/nklisch/claude-code-modesWhat 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 | $0.00038 | $0.00456 |
| Opus 5 | $0.00019 | $0.00228 |
| Sonnet 5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
structural-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 3d 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
Structural Refactor
Scan the codebase for organizational issues based on these structural rules. Each rule has a reference file with rationale, examples, and exceptions.
Rules
| Rule | Summary (one line) | Reference |
|---|---|---|
| Flat by Default | Keep src/ flat; group into subdirectories only when 3+ files share a concern | details |
| Soft 300-Line Limit | Implementation files should stay under 300 lines; split when single-domain logic exceeds it | details |
| Test Co-location | Unit tests next to source (file.test.ts); integration/e2e tests also in src/ | details |
| Centralized Types | All domain types/interfaces/enums in types.ts; no local type definitions | details |
| No Barrel Exports | No index.ts re-export files; always import directly from the source module | details |
| Prompt Domain Organization | Prompts organized by domain concept (axis/modifier), not by implementation | details |
| kebab-case Files | All source files use kebab-case; test files use {source}.test.ts suffix | details |
Output
Write the refactoring plan to docs/structural-refactor-plan.md.
The document should be a prioritized refactoring plan with these sections:
High Value
Implement-ready entries with file paths, current layout, target layout, and acceptance criteria.
Worth Considering
Valid reorganizations with moderate impact. Brief entries with paths and rationale.
Not Worth It
Code that technically violates a rule but should NOT be reorganized, with explanation why.
What ships with it
7 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.
- 3d ago First seen · 42 lines · 38 tokens per session scan A 1f5ed6d6068f
structural-refactor is a skill published in the GitHub repository nklisch/claude-code-modes (115 stars, last pushed 25d ago), licensed MIT. It adds 38 tokens to every session and 456 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 2026-08-30.
Other skills, from other repositories
client-setup
Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.
custom-features
Author a TanStack Table v9 feature plugin across every FeatureMap and API installation surface: state, options, column definitions, table, column, row, cell, header, row-model functions/caches, defaults, prototypes, and table/row/column instance data lifecycles. Load for initTableInstanceData, resetTableInstanceData…
effect-and-errors
Composing Effect programs, domain errors, HttpError, repository error types, or error propagation at HTTP boundaries.
migrate-better-result-3
Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
typescript-magician
Designs complex generic types, refactors any types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors. Use when the user asks about TypeScript (TS) types, generics, type inference, type guards, removing any types, strict typing, type errors, infer, extends…