Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it.
Install Scoped Change
$ npx skills add scarletkc/agents --skill scoped-change -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install scarletkc/agents scoped-change --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/scoped-change .claude/skills/scoped-change && rm -rf skills-srcUse ~/.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/
Install the "scoped-change" agent skill from https://github.com/scarletkc/agents/tree/main/skills/scoped-change into .claude/skills/scoped-change/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scoped-change", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/scarletkc/agents/tree/main/skills/scoped-changeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add scarletkc/agents --skill scoped-change -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install scarletkc/agents scoped-change --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/scoped-change .agents/skills/scoped-change && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scoped-change" agent skill from https://github.com/scarletkc/agents/tree/main/skills/scoped-change into .agents/skills/scoped-change/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scoped-change", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add scarletkc/agents --skill scoped-change -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install scarletkc/agents scoped-change --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/scoped-change .cursor/skills/scoped-change && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "scoped-change" agent skill from https://github.com/scarletkc/agents/tree/main/skills/scoped-change into .cursor/skills/scoped-change/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scoped-change", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/scarletkc/agents.git --path skills/scoped-change--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add scarletkc/agents --skill scoped-change -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install scarletkc/agents scoped-change --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/scoped-change .gemini/skills/scoped-change && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "scoped-change" agent skill from https://github.com/scarletkc/agents/tree/main/skills/scoped-change into .gemini/skills/scoped-change/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scoped-change", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install scarletkc/agents scoped-changeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add scarletkc/agents --skill scoped-change -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/scoped-change .github/skills/scoped-change && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "scoped-change" agent skill from https://github.com/scarletkc/agents/tree/main/skills/scoped-change into .github/skills/scoped-change/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scoped-change", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add scarletkc/agents --skill scoped-change -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install scarletkc/agents scoped-change --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/scoped-change .opencode/skills/scoped-change && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "scoped-change" agent skill from https://github.com/scarletkc/agents/tree/main/skills/scoped-change into .opencode/skills/scoped-change/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scoped-change", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
scoped-change- GitHub stars
- 226
- Token cost
- ~1.3k tokens
- SKILL.md length
- 740 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it.
- Scope is ambiguous
- SKILL.md covers Outside the boundary, Inside the boundary, When the boundary is unclear and Order of work
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- A diff touches neighboring surfaces
What it does
Scoped Change is an agent skill from scarletkc/agents. Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it. Use when scope is ambiguous, a diff touches neighboring surfaces, required dependent edits are unclear, or a proposed compatibility layer, migration, fallback, flag, abstraction, or parallel implementation may exceed the request.
Its SKILL.md is about 1.3k 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 Development. The repository describes itself as: Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents. The licence is Apache-2.0.
When your agent uses it
- Scope is ambiguous
- A diff touches neighboring surfaces
- Required dependent edits are unclear
- A proposed compatibility layer
Example prompts
- “/scoped-change”
What it can do on your machine
Read from SKILL.md and the folder at commit eb55005. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Scoped Change loads about 1.3k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 740 words of instructions outside code blocks.
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 scarletkc/agents at commit eb55005, republished under its Apache-2.0 licence (© scarletkc). 740 words, ~1,349 tokens.
Download SKILL.mdSave it as
.claude/skills/scoped-change/SKILL.md (or your agent's skills folder).- name
- scoped-change
- description
- Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it. Use when scope is ambiguous, a diff touches neighboring surfaces, required dependent edits are unclear, or a proposed compatibility layer, migration, fallback, flag, abstraction, or parallel implementation may exceed the request.
- license
- Apache-2.0
- metadata.author
- scarletkc
- metadata.source
- https://github.com/scarletkc/agents
- metadata.summary
- Hold a change to the size the request defines: no unrequested surfaces, no speculative layers, no half-applied edits.
Scoped Change
A change has one correct size and the request defines it. Overshooting and undershooting are the same failure — a boundary that was never located — and they fail differently: unrequested edits surface in review or in production, missing edits surface as the user finding them. Locate the boundary first, then be exhaustive inside it and inert outside it.
When the boundary is corrected mid-task, the result reads as though the
corrected scope were the only one there had ever been. A title, comment, or
rationale that keeps the dropped option alive re-imports the overshoot the
correction just removed, and the reader pays for it twice; what belongs in a
deliverable is
ux-writing.
Outside the boundary
- Edit only the surfaces the request names. A request that names one layer is a request about that layer, and the neighboring layers stay untouched even when they look wrong. Report what you noticed instead of fixing it; a separate observation is cheap, an entangled diff is not. Counter-example: asked to adapt a backend endpoint to an existing signup form, an agent redesigned the form too, and the reviewer had to pull the two apart before either could ship.
- Compatibility is a cost, and someone must already be paying it. Migrations, dual-read paths, deprecated aliases, and version shims are correct only when real users hold the old state. Establish that they exist before writing one; when they don't, a clean break is the smaller change. This is a question of fact, not caution. Counter-example: an unreleased product with no installed base got a save-format migration path for data no user had ever written, and the dead branch still had to be maintained and tested.
- Reuse the existing implementation; never add a second one beside it. If the project already renders this panel, formats this message, or awards this promotion, extend that path. A parallel implementation that looks correct is worse than an obvious gap, because it diverges silently and nothing fails when it does. Counter-example: a new promotion banner was written from scratch next to the existing level-up banner; a release later only one of them had the new animation.
- Prefer changing an existing rule to adding one next to it. A new constant, flag, or branch that coexists with the rule it was meant to replace leaves two sources of truth and doubles the states to reason about. Counter-example: a request to restrict upgrades to a single branch arrived as a new second rule constant; narrowing the meaning of the original constant was the entire change.
- Solve the stated problem, not its general form. Extension points, plugin layers, and configuration surfaces are worth building when a second caller exists, not when one is imagined. The simple implementation is the deliverable unless the request asked for the general one.
Show full SKILL.md (275 more words)Show less
Inside the boundary
- Apply the change at every site it implies. The requested behavior is the unit, not the file you happened to open. Before declaring it done, grep for the siblings of what you edited — the other cards of that type, the other localized strings of that key, the other callers of that helper — and confirm each one either changed or correctly didn't. Counter-example: a new card type shipped without the category prefix that every other card's label carries, so it read as a different kind of object in the UI.
- Matching the siblings is part of the request, not extra scope. A new item of an existing kind inherits that kind's required fields, naming convention, rarity or tier metadata, and text conventions without being told. Ask when the value is genuinely undetermined; don't ship the field missing. Counter-example: a new entity landed without the rarity field every sibling declares, and only surfaced when a loader that groups by rarity silently dropped it.
When the boundary is unclear
- Ask only for consequential boundary decisions. If the requested boundary cannot be determined without making a consequential choice the user has not already made, ask before crossing it. Routine implementation decisions stay with the agent and must not become confirmation gates.
Order of work
- Lock behavior in tests once it is settled, not while it is moving. Every behavior change still ships with happy-path and failure coverage; the point is sequence. Tests and docs written against logic that is still under discussion pin the wrong behavior and then argue for it, and the rewrite costs more than the wait. Get the logic confirmed, then cover it.
© scarletkc, 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/scoped-change of scarletkc/agents.
Open the folder on GitHubat commit eb55005
Compare with similar skills
Scoped Change 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Scoped Change this skillscarletkc/agents | 226 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from scarletkc/agents
All 11 skills in this repoAntigravity CLI
scarletkc/agents
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent.
Grok CLI
scarletkc/agents
Delegate bounded tasks to Grok Build from a supervising agent such as Codex.
Talk Like Scarletkc
scarletkc/agents
按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本，适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔，或在翻译中保留本人语气和立场时使用，无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。
Ask To Plan
scarletkc/agents
Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices.
Codex CLI
scarletkc/agents
When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model and reasoning effort.
Marketing Copy
scarletkc/agents
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls…
Related
Categories
Questions about Scoped Change
What does Scoped Change do?
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it. Scoped Change is an agent skill from scarletkc/agents. Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it.
When should I use Scoped Change?
Scoped Change fits situations like: scope is ambiguous; A diff touches neighboring surfaces; required dependent edits are unclear; A proposed compatibility layer.
How do I install Scoped Change in Claude Code?
Run `npx skills add scarletkc/agents --skill scoped-change -a claude-code`. Or copy the skill folder (skills/scoped-change in scarletkc/agents) into .claude/skills/scoped-change in your project. Claude Code loads it when a task matches its description.
How do I install Scoped Change in Codex?
Run `npx skills add scarletkc/agents --skill scoped-change -a codex`. Or copy the skill folder (skills/scoped-change in scarletkc/agents) into .agents/skills/scoped-change in your project. Codex loads it when a task matches its description.
Can I use Scoped Change 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 scarletkc/agents --skill scoped-change -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scoped-change, .gemini/skills/scoped-change, .github/skills/scoped-change and .opencode/skills/scoped-change in your project.
What does Scoped Change need to run?
SKILL.md names no scripts, command-line tools or credentials: Scoped Change is instructions for the agent only.
Does Scoped Change 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 Scoped Change 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 Scoped Change use?
Scoped Change is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Scoped Change use?
About 1.3k tokens (SKILL.md is roughly 5.4k 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 Scoped Change?
Skills that share tags, products or a category with Scoped Change: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Scoped Change?
scarletkc (a GitHub user) maintains it in scarletkc/agents, which has 226 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 21, 2026.
Source: scarletkc/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.