code-simplify

A guided process for making a limited section of code simpler while keeping its behavior unchanged.

In plain words
What is it for?
It helps simplify selected code, preserve its errors and side effects, review related tests, and report what changed and how it was validated.
Why use it?
It reduces unnecessary complexity without mixing in new features or unrelated refactoring. It also checks that the code still behaves as before.

Command

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 commands/jcarlosrodicio/opencode-agent-orchestration-kit/code-simplify
Clone the repo
git clone --depth 1 https://github.com/jcarlosrodicio/opencode-agent-orchestration-kit
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 204 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 $0.00008 $0.00204
Opus 5 $0.00004 $0.00102
Sonnet 5 $0.00002 $0.00041
Haiku 4.5 $0.00001 $0.00020

Measured 2d ago against content hash f42adc5c0756, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 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.

opencode/commands/code-simplify.md · 37 lines

What it actually says

Simplify this scope:

$ARGUMENTS

Use code-simplification.

Flow:

  1. Identify the exact scope and behavior that must be preserved.
  2. Read related code and tests before editing.
  3. Simplify only the requested code or code made unnecessarily complex by the current change.
  4. Preserve behavior, errors, side effects, and observable contracts.
  5. Run the most appropriate validation to prove behavior did not change.

Rules:

  • Do not make unrelated adjacent refactors.
  • Do not remove doubtful dead code without reporting it or asking for confirmation.
  • Do not mix simplification with new features.
  • If there is not enough coverage to preserve behavior confidently, state the risk and add a minimal test when scope allows.

Deliver:

  1. What was simplified.
  2. What behavior was preserved.
  3. Files touched.
  4. Validation run.
  5. Risks or code intentionally left untouched.
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. 2d ago First seen · 37 lines · 8 tokens per session scan A f42adc5c0756

Subscribe to this mod's changes

code-simplify is a command published in the GitHub repository jcarlosrodicio/opencode-agent-orchestration-kit (105 stars, last pushed 4d ago), licensed Apache-2.0. It adds 8 tokens to every session and 204 once invoked, about $0.0000 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.