simplify

simplify is a skill for Claude Code, Codex from genai-io/san. It costs 94 tokens per session (622 once invoked), scanned A, original, Apache-2.0.

A quality-focused review and cleanup of recently changed code. It looks for duplicated logic, awkward patterns, and unnecessary work while preserving the code's behavior.

In plain words
What is it for?
Use it after changing code to find reusable helpers, remove redundant state or work, and simplify repeated or improvised implementation patterns.
Why use it?
It helps make changes easier to maintain and more efficient without turning the review into a bug hunt or a broad redesign.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/genai-io/san/simplify
Any agent
npx skills add genai-io/san --skill simplify
Clone the repo
git clone --depth 1 https://github.com/genai-io/san

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for simplify

README.md
[![agentmods](https://agentmods.dev/badge/skills/genai-io/san/simplify.svg)](https://agentmods.dev/skills/genai-io/san/simplify)
Your own site
<a href="https://agentmods.dev/skills/genai-io/san/simplify"><img src="https://agentmods.dev/badge/skills/genai-io/san/simplify.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 622 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00094 $0.00622
Opus 5 $0.00047 $0.00311
Sonnet 5 $0.00019 $0.00124
Haiku 4.5 $0.00009 $0.00062

Measured 3d ago against content hash 419f5c41160c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simplify 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.

.san/personas/software-engineer/skills/simplify/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Simplify: quality cleanup on the changed code

Review the changed code for cleanups it would benefit from, then apply them. This is the quality pass — reuse, hacky patterns, wasted work. It is not the bug pass (code-review) and not a requested restructuring (refactor); stay in its lane and don't report correctness bugs or propose structural rewrites here.

Phase 1: Identify changes

Run git diff (or git diff HEAD when changes are staged). With no git changes, review the most recently modified files the user named or that you edited earlier in this conversation.

Phase 2: Review across three lenses (in parallel)

Use the Agent tool to launch three reviewers concurrently in one message (foreground). Give each the full diff. Each returns a short list of concrete, located findings.

  • Reuse. New code that duplicates an existing helper or utility; hand-rolled logic (string munging, path handling, env checks, type guards) that the codebase already has a function for. Point to the existing one to use instead.
  • Quality. Redundant state that could be derived; parameter sprawl instead of restructuring; near-duplicate blocks that should share an abstraction; leaky abstractions; stringly-typed code where a constant/enum exists; needless wrapper layers; conditionals nested 3+ deep (flatten with early returns or a lookup); comments that narrate WHAT instead of non-obvious WHY.
  • Efficiency. Redundant computation or repeated reads; independent work run sequentially that could be parallel; new blocking work on a startup or per-request hot path; unconditional no-op updates in loops/handlers (guard with change detection); pre-checking existence before operating (TOCTOU); unbounded growth or leaked resources; reading/loading far more than needed.

Phase 3: Apply the cleanups

Aggregate the findings and fix each directly. Keep each fix minimal and matched to the file's existing style. If a finding is a false positive or not worth it, skip it — don't argue with it. When done, briefly summarize what you cleaned up, or confirm the code was already clean.

Read the full file on GitHub · 59 lines

Changes

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.

  1. 3d ago First seen · 59 lines · 94 tokens per session scan A 419f5c41160c

Subscribe to this mod's changes

simplify is a skill published in the GitHub repository genai-io/san (75 stars, last pushed 6d ago), licensed Apache-2.0. It adds 94 tokens to every session and 622 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

pi-sync

Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.

sky-valley/pi · 66 tokens

dream-memory

Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.

LearnPrompt/cc-harness-skills · 37 tokens

kairos-lite

Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.

LearnPrompt/cc-harness-skills · 37 tokens

memory-extractor

Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.

LearnPrompt/cc-harness-skills · 28 tokens

structured-context-compressor

Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.

LearnPrompt/cc-harness-skills · 36 tokens

swarm-coordinator

Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.

LearnPrompt/cc-harness-skills · 36 tokens