run

A command that runs one Evolver improvement cycle in a Git repository. It gathers signals, chooses and changes reusable instructions called genes, and leaves proposed edits for review.

In plain words
What is it for?
Use it to run a self-improvement cycle, see which lessons and changes were selected, and prepare edits for approval or rollback.
Why use it?
It gives an agent a repeatable way to test improvements while keeping human approval separate. You can inspect the proposed changes before accepting them.

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/evomap/evolver-claude-code-plugin/run
Clone the repo
git clone --depth 1 https://github.com/EvoMap/evolver-claude-code-plugin
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 278 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 $0.00024 $0.00278
Opus 5 $0.00012 $0.00139
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured 2d ago against content hash eb27ef01bdcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run 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.

commands/run.md · 21 lines

What it actually says

Run an Evolver evolution cycle in the current git repository.

Steps:

  1. Confirm we're in a git repo (git rev-parse --is-inside-work-tree). If not, tell the user Evolver requires git and stop.
  2. Resolve the CLI and run it, passing through the user's flags. Execute:
EVOLVER="evolver"; command -v evolver >/dev/null 2>&1 || EVOLVER="npx -y @evomap/evolver"
EVOLVE_STRATEGY="${EVOLVE_STRATEGY:-balanced}" $EVOLVER run $ARGUMENTS
  1. Summarize what changed: which signals were collected, which gene was selected/mutated, and whether any changes are now pending solidify. If changes are pending, remind the user they can inspect and accept them with /evolver:review (or roll back with /evolver:review --reject).

Do not auto-approve pending changes — leave that to the user via /evolver:review.

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 · 21 lines · 24 tokens per session scan A eb27ef01bdcc

Subscribe to this mod's changes

run is a command published in the GitHub repository EvoMap/evolver-claude-code-plugin (12 stars, last pushed 12d ago), licensed MIT. It adds 24 tokens to every session and 278 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.