evolve

A command for reviewing and improving the configuration used by Claude Code, including its prompts, rules, tools, and agents.

In plain words
What is it for?
Use it to audit the setup, run a quick improvement cycle, perform a fuller evolution cycle, or scan for possible additions without changing anything.
Why use it?
It helps find setup problems and apply controlled improvements over time. It can also scan for new tools or patterns before making changes.

Command for Claude Code

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/liortesta/clawdagent/evolve
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 277 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 $0.00000 $0.00277
Opus 5 $0.00000 $0.00138
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00028

Measured 2d ago against content hash eef86bc3c9dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve 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.

.claude/commands/evolve.md · 37 lines

What it actually says

Evolve — Self-Evolution Cycle

Run a complete self-evolution cycle to improve the Claude Code setup.

Process:

Quick Evolve (default)

  1. Run self-improver agent → audit current setup
  2. Apply safe improvements (prompt tweaks, rule updates)
  3. Report changes

Full Evolve (with --full flag)

  1. Run scout agent → search for new tools, patterns, features
  2. Run self-improver agent → audit current setup
  3. Run evolution-engine agent → plan and execute evolution
  4. Validate all changes
  5. Git commit with evolution report

Usage:

  • /evolve — Quick self-improvement (5-10 min)
  • /evolve --full — Full evolution with external scanning (15-30 min)
  • /evolve --scout-only — Only scan for new tools, don't change anything
  • /evolve --audit-only — Only audit current setup, don't change anything

Guardrails:

  • ALWAYS git commit current state BEFORE evolving
  • NEVER auto-apply changes to security hooks
  • NEVER remove agents without logging
  • Show diff of all changes before final commit
  • Max 10 changes per evolution cycle (keep it manageable)

$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 · 37 lines · 0 tokens per session scan A eef86bc3c9dc

Subscribe to this mod's changes

evolve is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 277 tokens. 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.