agentmods.dev

auto-evolve

auto-evolve is a command for Claude Code from shwilliamson/automatasaurus. It costs 0 tokens per session (490 once invoked), scanned A, original, MIT.

A workflow step that creates project-specific instruction files for each coding agent from discovery and planning documents.

In plain words
What is it for?
Use it after project discovery and planning to regenerate each agent’s PROJECT.md file with tailored guidance.
Why use it?
It removes the need to write or update each agent’s project context by hand. It also checks that the required discovery and plan files exist first.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

not rated 5repo 8mo ago A scan 0 tokens original MIT

Good fit Use it after project discovery and planning to regenerate each agent’s PROJECT.md file with tailored guidance.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/shwilliamson/automatasaurus/auto-evolve
View source ↗ shwilliamson/automatasaurus
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.

Clone the repo
git clone --depth 1 https://github.com/shwilliamson/automatasaurus

Made for: Claude Code.

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 auto-evolve

README.md
[![agentmods](https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-evolve/github.svg)](https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-evolve)
Your own site
<a href="https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-evolve"><img src="https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-evolve/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for auto-evolve

Your own site · 80×15
<a href="https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-evolve"><img src="https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-evolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00490
Opus 5.5 $0.00000 $0.00196
Sonnet 5.5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 2mo ago against content hash 98b7caf8d92a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-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 2mo 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.

template/commands/auto-evolve.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve - Generate Agent Project Context

Generate project-specific context files for each agent based on discovery and planning outputs.

Workflow Mode

WORKFLOW_MODE: evolve

Instructions

You are now the Evolver. Your job is to:

  1. Read the discovery and planning outputs
  2. Generate tailored PROJECT.md files for each agent
  3. Report what was generated

Load Agent Role

Load your role from .claude/agents/evolver/AGENT.md

Prerequisites

Before running, verify planning files exist:

ls discovery.md discovery-*.md 2>/dev/null
ls implementation-plan.md implementation-plan-*.md 2>/dev/null

If no discovery or plan files are found, inform the user:

The evolve step requires:
- At least one discovery file (run /auto-discovery first)
- At least one implementation plan file (run /auto-plan first)

Which step would you like to run?

Execution

Follow the workflow in your AGENT.md:

  1. Read ALL discovery files (discovery.md, discovery-*.md) and ALL plan files (implementation-plan.md, implementation-plan-*.md)
  2. Check for design-system.md
  3. Fully regenerate PROJECT.md for each agent folder (always a complete regeneration, not incremental)
  4. Add a ## Recent Changes section at top summarizing what changed since last generation
  5. Generate PROJECT.md for each agent folder:
    • .claude/agents/developer/PROJECT.md
    • .claude/agents/architect/PROJECT.md
    • .claude/agents/designer/PROJECT.md
    • .claude/agents/tester/PROJECT.md
  6. Report completion

Output

Report to user:

**[Evolver]** Project context generated for all agents:

- .claude/agents/developer/PROJECT.md
- .claude/agents/architect/PROJECT.md
- .claude/agents/designer/PROJECT.md
- .claude/agents/tester/PROJECT.md

Agents will now have project-specific guidance when invoked.

Ready to start implementation with `/auto-work-all`.

Your Request

$ARGUMENTS

Begin by loading the evolver agent role, then check for required input files.

Read the full file on GitHub · 88 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. 2mo ago First seen · 88 lines · 0 tokens per session scan A 98b7caf8d92a

Subscribe to this mod's changes

auto-evolve is a command published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 490 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 2026-08-31.

Building agents
Related

auto-evolve compared with commands from other repositories

auto-evolve next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auto-evolveshwilliamson/automatasaurusCommand58mo agoMITA0Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code
convergegithub/spec-kitCommand148kyesterdayMITA35Claude Code
implementgithub/spec-kitCommand148kyesterdayMITA14Claude Code