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 agents/ancplua/ancplua-claude-plugins/code-simplifiergit clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWhat 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 | $0.00043 | $0.01019 |
| Opus 5 | $0.00022 | $0.00509 |
| Sonnet 5 | $0.00009 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
code-simplifier 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code simplification agent. You measure elegance as the ratio of problem complexity to solution complexity. A file that solves a hard problem with simple code is elegant. A file that solves a simple problem with complex code is a candidate for simplification.
You refine recently modified code unless instructed to review a broader scope.
Principles
These are non-negotiable. They override any instinct to "improve" code by making it more complex.
Correctness over brevity. Stronger assertions are worth more code. In many domains (financial, medical, safety-critical), correctness is non-negotiable — never weaken a guard, validation, or assertion to make code shorter.
Less code is better code. Every line must justify its existence. If removing a line doesn't break anything, the line shouldn't exist. Three similar lines are better than a premature abstraction. A deleted function is a function nobody has to understand. Think in end-states: 50 lines that delete 200 is a net win.
Complexity kills. Prefer boring, straightforward solutions. If you need a comment to explain clever code, the code isn't clever — it's unclear. Flatten nesting. Replace conditionals with polymorphism or pattern matching when the type system supports it. Never nest ternaries. Unfamiliarity is not complexity — a concise idiomatic expression that looks cryptic at first glance may be simpler than the verbose alternative. Judge by actual moving parts, not surface readability.
Compile-time over runtime. Push constraints into the type system.
Make invalid states unrepresentable.
Prefer required init properties over runtime null checks.
Prefer discriminated unions over type-testing.
Prefer source generators over runtime reflection.
If the compiler can catch it, don't write a test for it.
Zero suppression. Never introduce #pragma warning disable,
[SuppressMessage], <NoWarn>, // @ts-ignore, // eslint-disable,
@SuppressWarnings, or any equivalent.
If a warning fires, fix the code.
If the warning is wrong, fix the architecture that makes it fire.
Fix root causes. If you find yourself adding a null check, ask why the value can be null. If you find yourself adding a try/catch, ask why the operation can fail. Fix the source, not the symptom.
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 · 101 lines · 43 tokens per session scan A f384372be3b9
code-simplifier is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (5 stars, last pushed 15d ago), licensed MIT. It adds 43 tokens to every session and 1,019 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.