Agent skill

Self Modifying Code

by BuilderIO in BuilderIO/agent-native

Tiers, checkpoints, and off-limits paths for an agent editing the app's own source.

No licenceAuto-check: notes

Install Self Modifying Code

skills CLI
$ npx skills add BuilderIO/agent-native --skill self-modifying-code -a claude-code

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

GitHub CLI
$ gh skill install BuilderIO/agent-native self-modifying-code --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/BuilderIO/agent-native.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/self-modifying-code .claude/skills/self-modifying-code && 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
self-modifying-code
GitHub stars
7.1k
Token cost
~1.5k tokens
SKILL.md length
644 words
Files
1
Skills in repo
102
Repo updated
First seen
Licence
None found

At a glance

Tiers, checkpoints, and off-limits paths for an agent editing the app's own source.

  • Works in 5 steps: Commit or stash current state → Make the edit → Run pnpm typecheck && pnpm lint → …
  • Designing UI for agent editability
  • SKILL.md covers Rule, Why, Modification Taxonomy and Git Checkpoint Pattern, plus 3 more sections
  • Calls pnpm, git and npx

What it does

Self Modifying Code is an agent skill from BuilderIO/agent-native. Tiers, checkpoints, and off-limits paths for an agent editing the app's own source. Use when designing UI for agent editability, deciding whether a file is safe for the agent to change, or when tempted to patch config, .env, or an @agent-native/ package. Do not load it for ordinary source edits.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with pnpm. The repository describes itself as: A framework for building agentic apps.

When your agent uses it

  • Designing UI for agent editability
  • Deciding whether a file is safe for the agent to change
  • Tempted to patch config
  • An @agent-native/ package

Example prompts

  • “/self-modifying-code”

Requirements

  • Node.js

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Commit or stash current state
  2. Make the edit
  3. Run pnpm typecheck && pnpm lint
  4. If verification fails → revert with git checkout --
  5. If verification passes → continue

What it can do on your machine

Read from SKILL.md and the folder at commit e16da0c. 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:

    • pnpm
    • git
    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, git and npx, which can reach the network depending on how they are called.

    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

Self Modifying Code loads about 1.5k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 644 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:6
    hange, or when tempted to patch config, `.env`, or
  • NoteMentions a .env fileSKILL.md:32
    4: Off limits | Secrets and framework | `.env`, `@agent-native/*` packages & overrides   | Never modify these
  • NoteMentions a .env fileSKILL.md:99
    - Don't modify `.env` files or files containing secrets

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 644 words (~1,463 tokens).

“The agent can edit the app's own source code — components, routes, styles, scripts. This is a feature, not a bug. Design your app expecting this.”

— opening of SKILL.md by BuilderIO
name
self-modifying-code
scope
dev
metadata.internal
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/self-modifying-code of BuilderIO/agent-native.

Open the folder on GitHubat commit e16da0c

Compare with similar skills

Self Modifying Code 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.

Self Modifying Code compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Self Modifying Code this skillBuilderIO/agent-native7.1k—~1.5kAutomated safety check: NotesNone
DeerFlow Smoke Testbytedance/deer-flow83k—~2.5kAutomated safety check: NotesMIT
@pierre/diffs Code Renderingpierrecomputer/pierre6.2k2 repos~803Automated safety check: PassApache-2.0
React Router Release Notes Prepremix-run/react-router57k—~1.1kAutomated safety check: PassMIT
Vuetify Playgroundvuetifyjs/vuetify41k—~730Automated safety check: PassCustom licence
React Syncvercel/next.js143k—~486Automated safety check: PassMIT

Similar skills

  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    83k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes
  • @pierre/diffs Code Rendering

    pierrecomputer/pierre

    Guides an agent through using @pierre/diffs to render syntax-highlighted files and diffs, and to build editing and review surfaces in React or plain JavaScript.

    6.2k GitHub starsUsed in 2 repos~803 tokens
    DevelopmentAuto-check passed
  • React Router Release Notes Prep

    remix-run/react-router

    Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.

    57k GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Vuetify Playground

    vuetifyjs/vuetify

    Maintains the Vuetify repo's local Playground.vue so contributors get a realistic reproduction and a short demo they can paste into a pull request description.

    41k GitHub stars~730 tokensUpdated today
    Frontend & DesignAuto-check passed
  • React Sync

    vercel/next.js

    Official

    Build local React changes in the bundle variants consumed by Next.js, sync them into a local Next.js checkout, and test the resulting integration.

    143k GitHub stars~486 tokensUpdated today
    Auto-check passed
  • Link Workspace Packages

    nomcopter/react-mosaic

    Link workspace packages in monorepos (npm, yarn, pnpm, bun).

    4.8k GitHub starsUsed in 6 repos~760 tokens
    DevelopmentAuto-check passed

More from BuilderIO/agent-native

All 102 skills in this repo
  • Actions

    BuilderIO/agent-native

    How to create and run agent actions. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Client Methods

    BuilderIO/agent-native

    Client method surface rules. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Adding A Feature

    BuilderIO/agent-native

    The four-area checklist every new feature must complete. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Address Feedback

    BuilderIO/agent-native

    Triage feedback from docs, issues, Slack threads, or pasted notes into verified bugs, UX proposals, unclear questions, and skipped noise.

    7.1k GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Audit Log

    BuilderIO/agent-native

    Durable, access-scoped, append-only record of who changed what app data, when, and whether it was the agent or a human.

    7.1k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Automations

    BuilderIO/agent-native

    Event-triggered and schedule-triggered automations with natural-language conditions.

    7.1k GitHub stars~4.4k tokensUpdated today
    Auto-check passed

Works with

Questions about Self Modifying Code

What does Self Modifying Code do?

Tiers, checkpoints, and off-limits paths for an agent editing the app's own source. Self Modifying Code is an agent skill from BuilderIO/agent-native. Tiers, checkpoints, and off-limits paths for an agent editing the app's own source.

When should I use Self Modifying Code?

Self Modifying Code fits situations like: designing UI for agent editability; deciding whether a file is safe for the agent to change; tempted to patch config; an @agent-native/ package.

How do I install Self Modifying Code in Claude Code?

Run `npx skills add BuilderIO/agent-native --skill self-modifying-code -a claude-code`. Or copy the skill folder (.agents/skills/self-modifying-code in BuilderIO/agent-native) into .claude/skills/self-modifying-code in your project. Claude Code loads it when a task matches its description.

How do I install Self Modifying Code in Codex?

Run `npx skills add BuilderIO/agent-native --skill self-modifying-code -a codex`. Or copy the skill folder (.agents/skills/self-modifying-code in BuilderIO/agent-native) into .agents/skills/self-modifying-code in your project. Codex loads it when a task matches its description.

Can I use Self Modifying Code 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 BuilderIO/agent-native --skill self-modifying-code -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/self-modifying-code, .gemini/skills/self-modifying-code, .github/skills/self-modifying-code and .opencode/skills/self-modifying-code in your project.

What does Self Modifying Code need to run?

Going by SKILL.md and its folder, Self Modifying Code needs the command-line tools its instructions call (pnpm, git and npx). Our summary lists: Node.js.

Does Self Modifying Code access the network?

SKILL.md contains no URLs. Its commands use git and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Self Modifying Code safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Self Modifying Code use?

No licence was found for Self Modifying Code or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Self Modifying Code use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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 Self Modifying Code?

Skills that share tags, products or a category with Self Modifying Code: DeerFlow Smoke Test (bytedance/deer-flow, 83k stars), @pierre/diffs Code Rendering (pierrecomputer/pierre, 6.2k stars), React Router Release Notes Prep (remix-run/react-router, 57k stars) and Vuetify Playground (vuetifyjs/vuetify, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Self Modifying Code?

BuilderIO (a GitHub organization) maintains it in BuilderIO/agent-native, which has 7,087 GitHub stars. The repository holds 102 skills in this directory. The repository was last updated on October 8, 2026.

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