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 nanparth/ai-skill-hub --skill tech-refactorgit clone --depth 1 https://github.com/nanparth/ai-skill-hubWrote 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/nanparth/ai-skill-hub/tech-refactor)<a href="https://agentmods.dev/skills/nanparth/ai-skill-hub/tech-refactor"><img src="https://agentmods.dev/badge/skills/nanparth/ai-skill-hub/tech-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/nanparth/ai-skill-hub/tech-refactor"><img src="https://agentmods.dev/badge/skills/nanparth/ai-skill-hub/tech-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 | $0.00082 | $0.03484 |
| Opus 5.5 | $0.00033 | $0.01394 |
| Sonnet 5.5 | $0.00016 | $0.00697 |
| Haiku 4.5 | $0.00008 | $0.00348 |
Grade A, and why
tech-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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⛔ GATE DISCIPLINE: host user-choice mechanism gates = hard stops. Never skip or auto-pick answer. Tool unavailable → numbered-text fallback → stop, wait for reply. No flag bypasses a gate; override flags pass only as user's recorded gate answer.
/tech-refactor
Release version: 1.4.0
Architectural overhaul of existing systems. 5-phase analysis → subagent execution with TDD and two-stage review.
Core principle: Deletion is the proof of centralization. Adding a new abstraction is not centralization. The old access path must be removed before centralization is complete.
Frontend changes = user-verified. A model cannot see a rendered UI. Any dashboard/view change closes with a numbered visual checklist for the user, not a claimed visual pass.
Not for: surgical cleanup, single-function improvements, extract/rename/DRY — use /simplify.
Pipeline
Phase 1 — Understand → confidence-rated behavioural inventory
Phase 2 — Audit → risk findings + additive-bias detection
Phase 3 — Clarify → targeted questions (conditional — skip if nothing unclear)
Phase 4 — Design → target architecture + migration strategy + legacy path retirement plan
Phase 5 — Roadmap → execution-ready task list
⛔ user approval gate
Execute → independent implementer dispatch per task, sequential (see Execution)
Workflow
- Phase 1 — Understand ⛔ BLOCKING
- 1.1 Read target codebase: entry points, module structure, key files
- 1.2 Produce confidence-rated inventory (high/medium/low):
- User-facing features, inputs, outputs, side effects
- External integrations, API shapes, wire formats, config keys, implicit contracts
- Data models, schemas, business rules, domain rules
- Duplicate implementations or competing sources of truth
- Current tests and what behaviour they protect
- 1.3 Present inventory to user; verdict via a structured choice prompt ⛔ BLOCKING (options: Proceed (Recommended) / Clarify; fallback: numbered text options). Inventory >40 lines → inventory message ends the turn; raise the gate next turn with ≤5-line digest.
What ships with it
13 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.
- PORTABILITY.md 3.0 KB
- references/architectural-risk-audit.md 7.6 KB
- references/code-smells.md 1.2 KB
- references/cross-boundary-refactoring.md 1.0 KB
- references/design-patterns.md 536 B
- references/legacy-path-retirement.md 8.3 KB
- references/parse-dont-validate.md 1.3 KB
- shared/code-organization.md 6.6 KB
- shared/technical-delivery-doctrine.md 9.5 KB
- shared/technical-delivery-runtime-adapter.md 6.3 KB
- shared/technical-delivery-test-level.md 3.4 KB
- shared/test-level-protocol.md 3.4 KB
- tech-refactor-readme.md 4.7 KB
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 Changed · +60 lines · +15 tokens per session a708fc3b9f18
- 1mo ago First seen · 87 lines · 67 tokens per session scan A 336c1058cf80
tech-refactor is a skill published in the GitHub repository nanparth/ai-skill-hub (23 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 3,484 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…