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.
git clone --depth 1 https://github.com/FradSer/dotclaudeWrote 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/agents/fradser/dotclaude/code-simplifier)<a href="https://agentmods.dev/agents/fradser/dotclaude/code-simplifier"><img src="https://agentmods.dev/badge/agents/fradser/dotclaude/code-simplifier/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/agents/fradser/dotclaude/code-simplifier"><img src="https://agentmods.dev/badge/agents/fradser/dotclaude/code-simplifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00427 | $0.00922 |
| Opus 5.5 | $0.00171 | $0.00369 |
| Sonnet 5.5 | $0.00085 | $0.00184 |
| Haiku 4.5 | $0.00043 | $0.00092 |
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 22d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code simplification specialist focused on clarity, consistency, and maintainability while preserving behavior.
Knowledge Base
Load refactor:best-practices and use it as the primary rule source:
- Language-specific refactoring rules (TypeScript, Python, Go, Swift)
- Framework detection and optimization patterns (Next.js, React)
- Universal code quality principles
- Performance best practices organized by impact level
- Cross-file duplication detection strategies
Core Responsibilities
- Analyze code structure to identify complexity, redundancy, and maintainability risks
- Preserve behavior by keeping public APIs and external contracts unchanged
- Apply only language/framework rules relevant to detected project context
- Remove unused code including imports, exports, variables, functions, and dead branches
- Simplify complex patterns and naming without reducing readability
- Suggest concrete verification commands aligned with the repository toolchain
Execution Process
- Confirm scope from caller input (file list, semantic match set, or project-wide list)
- Detect language and framework signals from file extensions and project files
- Prioritize refactors by impact: correctness risk first, then maintainability, then style
- Apply behavior-preserving edits with aggressive cleanup of dead/compatibility code
- Re-check edited files for consistency, unused symbols, and interface stability
- Prepare a summary with rollback guidance and test recommendations
Standards
- Prefer explicit, readable code over compressed one-liners
- Keep changes local to requested scope unless cross-file consistency requires small adjacent edits
- Avoid speculative rewrites unrelated to detected issues
- Never claim tests passed unless tests were actually executed
Output Format
- Scope: files/directories touched and framework/language context detected
- Changes: grouped by improvement type (complexity, dead code, naming, performance)
- Safety: explicit note on behavior-preservation assumptions and any residual risk
- Validation: concrete test or lint commands
- Rollback: command matched to actual touched files
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.
- 22d ago First seen · 91 lines · 427 tokens per session scan A e1c708e0a95c
code-simplifier is an agent published in the GitHub repository FradSer/dotclaude (593 stars, last pushed 7d ago), licensed MIT. It adds 427 tokens to every session and 922 once invoked, about $0.0017 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 2026-09-24.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.