optimize

A command that starts evo’s autoresearch optimization loop, an automated cycle for trying changes and evaluating experiments.

In plain words
What is it for?
Use it to start the loop and pass options such as the number of subagents, the experiment budget, or autonomous mode.
Why use it?
It provides an entry point for running the optimization process without manually coordinating each experiment.

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/evo-hq/evo/optimize
Clone the repo
git clone --depth 1 https://github.com/evo-hq/evo
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 107 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 $0.00011 $0.00107
Opus 5 $0.00005 $0.00053
Sonnet 5 $0.00002 $0.00021
Haiku 4.5 $0.00001 $0.00011

Measured 2d ago against content hash 852fe68fbd10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimize 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.

plugins/evo/commands/optimize.md · 11 lines

What it actually says

Load and follow the evo optimize skill (named optimize under the evo plugin in your skill registry — use your skill loader, not a filesystem path). It drives the structured experiment loop: the orchestrator writes briefs and spawns subagents that own the candidate edits and runs.

Any arguments below are parameters for that skill (e.g. subagents=N, budget=N, autonomous).

$ARGUMENTS

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 · 11 lines · 11 tokens per session scan A 852fe68fbd10

Subscribe to this mod's changes

optimize is a command published in the GitHub repository evo-hq/evo (1,438 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 107 once invoked, about $0.0001 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.