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 Kevin-Liu-01/Agent-Machines --skill stage-refactor-checklistgit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/stage-refactor-checklist)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/stage-refactor-checklist"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/stage-refactor-checklist/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/kevin-liu-01/agent-machines/stage-refactor-checklist"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/stage-refactor-checklist.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 | $0.00045 | $0.03350 |
| Opus 5 | $0.00023 | $0.01675 |
| Sonnet 5 | $0.00009 | $0.00670 |
| Haiku 4.5 | $0.00005 | $0.00335 |
Grade A, and why
stage-refactor-checklist 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 8d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage Refactor Checklist
Systematic checklist for refactoring a schema_compiler stage folder. Derived from the frontend/ reference implementation and the feedback that shaped it.
Prerequisites (do these BEFORE writing any code)
- Read
style/style.mdand the column-aligned-fields skill. - Read EVERY file in the target folder to map the full topology.
- Grep the entire repo for all imports from this stage to understand consumers.
- Identify: what is this stage called, who are the actors, which verbs do they get?
- Ask: is the current class a thin wrapper over module-level functions? If yes, the class needs to absorb all logic (see "Class cohesion" below).
Architecture Principles
Contract changes between stages are fine
Don't preserve old interfaces for backward compatibility. If the right design requires a new method signature, a renamed function, or a restructured IR type, make the change and update every consumer. The only constraint is that you can answer: what is this stage called, who are the actors, which verbs do they get?
Class cohesion
The stage class is the cohesive unit. It is NOT a thin wrapper that delegates to module-level functions. ALL logic belongs inside the class as methods.
- If the class has 2-3 methods and 8 free functions do the real work, the class is a facade. Move the functions in.
- Prefer public methods. If a method is part of the stage's interface (i.e.,
you'd want to call it in a test or from another stage), it's public. Only use
_prefix for true implementation internals that callers never need. - Pure methods that don't use
selfget@staticmethod. This signals purity while keeping them colocated. - Standalone pure utilities (like
_to_snake_case) may stay module-level if genuinely independent of the class. - No module-level convenience functions or
_default_instancepatterns. Callers instantiate the class directly. - Use
# --- Label ---section headers inside the class to group related methods (e.g.,# --- Entry point ---,# --- Resolution ---,# --- Helpers ---).
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.
- 8d ago First seen · 280 lines · 45 tokens per session scan A d9c18483d61b
stage-refactor-checklist is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 3,350 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 2026-09-03.
Other skills, from other repositories
app-debug-workflow
⚠️ TRIGGER: when auditing an unfamiliar full-stack codebase for bugs — security, performance, reliability, dev tooling. Multi-session workflow: discover → duck-verify → plan → handoff → fix → validate. 90-min timebox. Designed for time-pressure coding/debug tasks.
code-simplifier
Review substantial mcp-reporter changes for unnecessary complexity while preserving tested behavior and public contracts.
vicious-mockery
The bard's cantrip that deals psychic damage through insults. In practice this is adversarial review — the art of finding and articulating exactly what is wrong with something in a way that is impossible to ignore. Unlike polite feedback that gets filed and forgotten, vicious mockery lands. It is the red-team report…
grill-with-docs
Cross-examine codebase architecture against official library documentation and API specs. Identifies deprecations, anti-patterns, and suboptimal library usage.
code
Use BEFORE generating, refactoring, reviewing, or debugging code. Trigger phrases include "write a function/script/class for X", "review this code/diff/PR", "refactor this", "debug this error", "is this implementation correct", "what's wrong with this code", "improve this code", "translate from X to Y", or any prompt…
engineering-incident-response-commander
An incident-response guide for managing production failures, coordinating responders, reviewing what happened afterward, and tracking service targets. SLOs and SLIs are measures used to define and monitor service reliability.