Agent skill

Evolve

by teddytennant in teddytennant/wizard

How to extend Wizard via /evolve. An agent skill from teddytennant/wizard.

Apache-2.0Auto-check passedAgent Workflows

Install Evolve

skills CLI
$ npx skills add teddytennant/wizard --skill evolve -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install teddytennant/wizard evolve --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/teddytennant/wizard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evolve .claude/skills/evolve && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
evolve
GitHub stars
103
Token cost
~835 tokens
SKILL.md length
308 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

How to extend Wizard via /evolve. An agent skill from teddytennant/wizard.

  • Tasks that involve Subagents
  • SKILL.md covers Picking a tier, Tier 1 channels, Tier 2 — deep evolve and Always
  • Calls cargo
  • Tasks that involve MCP servers

What it does

Evolve is an agent skill from teddytennant/wizard. How to extend Wizard via /evolve. Cheapest tier first — skills, MCP, scripted tools, subagents; deep recompile only when the binary must change.

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents and MCP servers. It works with Model Context Protocol and Lua. The repository describes itself as: The fastest agent in your terminal: one Rust binary, any model. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Subagents
  • Tasks that involve MCP servers

Example prompts

  • “/evolve”

What it can do on your machine

Read from SKILL.md and the folder at commit 9d123be. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • cargo

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Evolve loads about 835 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 308 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~835

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from teddytennant/wizard at commit 9d123be, republished under its Apache-2.0 licence (© teddytennant). 308 words, ~835 tokens.

Download SKILL.mdSave it as .claude/skills/evolve/SKILL.md (or your agent's skills folder).
name
evolve
description
How to extend Wizard via /evolve. Cheapest tier first — skills, MCP, scripted tools, subagents; deep recompile only when the binary must change.

Self-extension (/evolve)

Add capabilities through the cheapest tier that works. Tier 1 = files under ~/.wizard/, live on /reload, reverted by deleting the file. Tier 2 (deep=true) recompiles Wizard and should be uncommon.

Picking a tier

Capability is…ChannelRecompile?
Knowledge, workflow, domain guidelinesSkillNo
External (browser, computer use, DB, search)MCP serverNo
Small glue / project automationScripted toolNo
Specialized sub-worker (own prompt/budget)SubagentNo
Change to built-in behavior or UIDeep (deep=true)Yes

If an MCP server or script can do it, stay Tier 1.

Tier 1 channels

Skills

~/.wizard/skills/<name>/SKILL.md — optional name/description frontmatter, then an imperative markdown body. The prompt lists name and description; the body is read from disk when the skill matches. Set always: true to inline the body. Set when_env: VAR1, VAR2 to omit the skill unless one of those variables is set. User skills shadow bundled names.

MCP servers

Append to ~/.wizard/mcp.toml:

toml
[[server]]
name = "computer-use"
transport = "stdio"        # or "http" with url = "..."
command = "uvx"
args = ["mcp-computer-use"]

/reload merges tools (server__tool on collision). Verify command/url exists before registering.

Scripted tools (LuaJIT)

~/.wizard/tools/<name>.toml + .lua. Prefer LuaJIT in-process; external interpreters only when the job needs the host shell or a native CLI.

toml
name = "slugify"
description = "Slugify a string"
script = "slugify.lua"
runtime = "luajit"

[parameters]
type = "object"
required = ["text"]
[parameters.properties.text]
type = "string"
lua
local s = tostring(args.text or ""):lower()
s = s:gsub("[^%w]+", "-"):gsub("^%-", ""):gsub("%-$", "")
print(s)

Globals: args, cwd, wizard.read_file / write_file / json_encode / json_decode / runtime. print → stdout; non-nil return if nothing printed. Prefix error: for soft failure. Test once before declaring done.

Subagents

~/.wizard/subagents/<name>.toml:

toml
name = "reviewer"
description = "Audits diffs for security issues"
system_prompt = "You are a security reviewer. Report findings with file:line."
# tool_scope = ["read_file", "search_files", "git_diff"]
# max_steps = 0   # 0/omit = unlimited

Keep tool_scope narrow; subagents run auto-approved in isolated context.

Tier 2 — deep evolve

Only for new Rust in core (built-in tool kind, protocol, TUI). Pipeline: checkout ~/.wizard/src, provision toolchain if needed, diff, cargo build --release, exec-replace. If source/toolchain cannot be provisioned, fall back to Tier 1 and say so — do not fail silently.

Always

  • Log to ~/.wizard/evolution.jsonl; tell the user what was added and where.
  • One file/block per capability (independently reversible).
  • After write: /reload and confirm presence before claiming success.
  • MCP and scripts run with the user's privileges — prefer well-known servers and small auditable scripts; never add unrequested capabilities.

© teddytennant, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/evolve of teddytennant/wizard.

Open the folder on GitHubat commit 9d123be

Compare with similar skills

Evolve next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Evolve compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Evolve this skillteddytennant/wizard103—~835Automated safety check: PassApache-2.0
Claude Automation Recommenderanthropics/claude-plugins-official38k3 repos~2.7kAutomated safety check: NotesApache-2.0
CC Workflow Studio AI Editorbreaking-brake/cc-wf-studio5.4k—~561Automated safety check: PassCustom licence
Agent Deckasheshgoplani/agent-deck1k—~1.7kAutomated safety check: PassMIT
Bootstrapinfragate/capa724—~5.9kAutomated safety check: PassMIT
Puppetmaster Agent Orchestrationprofessorpalmer/Puppetmaster467—~3.2kAutomated safety check: PassMIT

Similar skills

  • Claude Automation Recommender

    anthropics/claude-plugins-official

    Official

    Scans a codebase and suggests which Claude Code hooks, subagents, skills, plugins and MCP servers fit its stack, without changing any files.

    38k GitHub starsUsed in 3 repos~2.7k tokens
    Agent WorkflowsAuto-check: notes
  • CC Workflow Studio AI Editor

    breaking-brake/cc-wf-studio

    Creates and edits visual agent workflows in CC Workflow Studio through conversation, with the agent reading and writing the canvas over MCP.

    5.4k GitHub stars~561 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Agent Deck

    asheshgoplani/agent-deck

    agent-deck, the terminal session manager for AI coding agents.

    1k GitHub stars~1.7k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Bootstrap

    infragate/capa

    Capify an existing project. An agent skill from infragate/capa.

    724 GitHub stars~5.9k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed
  • Puppetmaster Agent Orchestration

    professorpalmer/Puppetmaster

    Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.

    467 GitHub stars~3.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Agentforce Generate

    SalesforceAIResearch/agentforce-adlc

    Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script.

    114 GitHub starsUsed in 1 repo~7.4k tokens
    Agent WorkflowsAuto-check passed

More from teddytennant/wizard

  • Plain Writing

    teddytennant/wizard

    Write prose that reads like a person wrote it, not a model. An agent skill from teddytennant/wizard.

    103 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Conventional Commit

    teddytennant/wizard

    Write a conventional commit subject and body from the current diff.

    103 GitHub stars~501 tokensUpdated today
    Auto-check passed
  • PR Description

    teddytennant/wizard

    Write a pull-request title and body from the current branch against its base.

    103 GitHub stars~484 tokensUpdated today
    Auto-check passed
  • Undercover

    teddytennant/wizard

    Keep git history clean in public repos. An agent skill from teddytennant/wizard.

    103 GitHub stars~335 tokensUpdated today
    Auto-check passed
  • Coding

    teddytennant/wizard

    Baseline coding workflow. An agent skill from teddytennant/wizard.

    103 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Categories

Questions about Evolve

What does Evolve do?

How to extend Wizard via /evolve. An agent skill from teddytennant/wizard. Evolve is an agent skill from teddytennant/wizard. How to extend Wizard via /evolve.

When should I use Evolve?

Evolve fits situations like: tasks that involve Subagents; tasks that involve MCP servers.

How do I install Evolve in Claude Code?

Run `npx skills add teddytennant/wizard --skill evolve -a claude-code`. Or copy the skill folder (skills/evolve in teddytennant/wizard) into .claude/skills/evolve in your project. Claude Code loads it when a task matches its description.

How do I install Evolve in Codex?

Run `npx skills add teddytennant/wizard --skill evolve -a codex`. Or copy the skill folder (skills/evolve in teddytennant/wizard) into .agents/skills/evolve in your project. Codex loads it when a task matches its description.

Can I use Evolve in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add teddytennant/wizard --skill evolve -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evolve, .gemini/skills/evolve, .github/skills/evolve and .opencode/skills/evolve in your project.

What does Evolve need to run?

Going by SKILL.md and its folder, Evolve needs the command-line tools its instructions call (cargo).

Does Evolve access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Evolve safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Evolve use?

Evolve is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Evolve use?

About 835 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Evolve?

Skills that share tags, products or a category with Evolve: Claude Automation Recommender (anthropics/claude-plugins-official, 38k stars), CC Workflow Studio AI Editor (breaking-brake/cc-wf-studio, 5.4k stars), Agent Deck (asheshgoplani/agent-deck, 1k stars) and Bootstrap (infragate/capa, 724 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evolve?

teddytennant (a GitHub user) maintains it in teddytennant/wizard, which has 103 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.

Source: teddytennant/wizard on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.