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.
npx agentmods add commands/shwilliamson/automatasaurus/auto-evolvegit clone --depth 1 https://github.com/shwilliamson/automatasaurusWrote 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.
[](https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-evolve)<a href="https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-evolve"><img src="https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-evolve.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00490 |
| Opus 5 | $0.00000 | $0.00245 |
| Sonnet 5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
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 3d 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.
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:
- Read the discovery and planning outputs
- Generate tailored PROJECT.md files for each agent
- 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:
- Read ALL discovery files (
discovery.md,discovery-*.md) and ALL plan files (implementation-plan.md,implementation-plan-*.md) - Check for design-system.md
- Fully regenerate PROJECT.md for each agent folder (always a complete regeneration, not incremental)
- Add a
## Recent Changessection at top summarizing what changed since last generation - 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
- 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.
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.
- 3d ago First seen · 88 lines · 0 tokens per session scan A 98b7caf8d92a
auto-evolve is a command published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 6mo 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.