New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Kc Scope PR

by imran31415 in imran31415/kube-coder

Scope a kube-coder change before you open or update a PR — what the diff actually touches, which tests reach it, what the change made worse, and what is left untested.

MITAuto-check: notesDevelopment

Install Kc Scope PR

skills CLI
$ npx skills add imran31415/kube-coder --skill kc-scope-pr -a claude-code

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

GitHub CLI
$ gh skill install imran31415/kube-coder kc-scope-pr --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/imran31415/kube-coder.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/kc-scope-pr .claude/skills/kc-scope-pr && 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
kc-scope-pr
GitHub stars
388
Token cost
~1.2k tokens
SKILL.md length
539 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Scope a kube-coder change before you open or update a PR — what the diff actually touches, which tests reach it, what the change made worse, and what is left untested.

  • Works in 4 steps: Run the tests it names, not the ones you… → Put impacted= in the PR body when it is… → Fix or justify each --quality-delta row.… → …
  • Tasks that involve Codebase onboarding
  • SKILL.md covers Why this exists, The three calls, Reading the output and What to do with it, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Kc Scope PR is an agent skill from imran31415/kube-coder. Scope a kube-coder change before you open or update a PR — what the diff actually touches, which tests reach it, what the change made worse, and what is left untested. Use after the code is written and before kc-preflight/kc-ship-pr, so the PR description and the tests you run come from the call graph rather than from memory. Also the answer to "is this diff bigger than I think?" and "which tests should I run for this?".

Its SKILL.md is about 1.2k 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, covering Codebase onboarding and Pull requests. The repository describes itself as: helm chart for a isolated dev coding environment pod in kubernetes. The licence is MIT.

When your agent uses it

  • Tasks that involve Codebase onboarding
  • Tasks that involve Pull requests

Example prompts

  • “is this diff bigger than I think?”
  • “which tests should I run for this?”
  • “/kc-scope-pr”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, Read

Workflow steps

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

  1. Run the tests it names, not the ones you remember. If tests= lists a
  2. Put impacted= in the PR body when it is large. A reviewer seeing
  3. Fix or justify each --quality-delta row. Do not game the number; a
  4. Treat untested= rows as the test-writing list, highest ccx first.

What it can do on your machine

Read from SKILL.md and the folder at commit fc0b886. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    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

Kc Scope PR loads about 1.2k tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 539 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read

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 imran31415/kube-coder at commit fc0b886, republished under its MIT licence (© imran31415). 539 words, ~1,161 tokens.

Download SKILL.mdSave it as .claude/skills/kc-scope-pr/SKILL.md (or your agent's skills folder).
name
kc-scope-pr
description
Scope a kube-coder change before you open or update a PR — what the diff actually touches, which tests reach it, what the change made worse, and what is left untested. Use after the code is written and before kc-preflight/kc-ship-pr, so the PR description and the tests you run come from the call graph rather than from memory. Also the answer to "is this diff bigger than I think?" and "which tests should I run for this?".
allowed-tools
Bash, Read
user-invocable
true
argument-hint
[paths…] (default: the current git diff)

Scope a PR with ripwire

Run after the change is written, before kc-preflight and kc-ship-pr.

ripwire is baked into the image (/usr/local/bin/ripwire, pinned in devlaptop/Dockerfile). Zero deps, and the whole workspace chart — 522 files, 10k symbols — maps in under two seconds, so this is cheap enough to run on a one-file change.

Why this exists

This repo has repeatedly shipped changes whose blast radius was larger than the diff looked. Two from recent history, both of which this skill's output would have named up front:

  • A run-preflight guard was added to BoardRunsManager.create and four board test suites created runs, not one. CI went red with 64 failures and 29 errors while the same tests passed locally.
  • mcp_dashboard.py and server.py disagreed about one constant. Nothing in either file's diff said the other existed.

The point is not the numbers, it is the direction: --test-gate answers "which tests reach what I touched" from the call graph, which is the question a human answers from memory and gets wrong.

The three calls

Scope is one root at a time. charts/workspace is the usual one; use charts/workspace-controller for controller work.

bash
ROOT=charts/workspace

# 1. What does this change actually reach, and which tests cover it?
#    Defaults to the git diff. exit 4 = there are tests to run or untested
#    blast radius; that is an obligation, not a failure.
ripwire "$ROOT" --test-gate

# 2. What did I make WORSE? exit 2 only on a pre-existing symbol regressing.
#    A `new-symbol` row never gates — it is still your debt, so read it.
ripwire "$ROOT" --quality-delta

# 3. Did I change a contract someone depends on? (per symbol, ~ms)
ripwire "$ROOT" --edit-check=SomeChangedSymbol

--situ is the same information as --test-gate without the gate, for mid-task orientation rather than a pre-PR check.

Reading the output

It is minified XML with a long self-describing header comment — the header explains every attribute, so read it once rather than guessing. The attributes that carry the decision:

attributemeaning
changed=files in the diff
impacted=symbols transitively reaching them — the real blast radius
tests=test files that reach the change; each <t> may carry run="<cmd>"
untested=impacted symbols no test reaches — <u> rows, worst first by ccx
gating= on quality-deltaregressions that will fail the gate

counts_floor="1" means every count is a floor, not a total: dynamic dispatch and script-invoked harnesses are not call edges. untested=0 is therefore "nothing the graph can see", never "fully covered".

Show full SKILL.md (225 more words)Show less

What to do with it

  1. Run the tests it names, not the ones you remember. If tests= lists a suite you did not expect, that is the finding — go look at why it reaches your change before assuming the tool is wrong.
  2. Put impacted= in the PR body when it is large. A reviewer seeing "3 files changed" and a four-figure blast radius reads the diff differently.
  3. Fix or justify each --quality-delta row. Do not game the number; a wrong abstraction beats a good score.
  4. Treat untested= rows as the test-writing list, highest ccx first.

Then hand off: kc-preflight runs the suites for real, kc-ship-pr opens the PR.

Honest limits

  • A floor, never a total. Reflection, dynamic dispatch, and the shell harnesses under tests/ are invisible to a static call graph. --test-gate reports script_gates_unmodelled= for exactly this reason. It narrows what you must think about; it does not replace thinking.
  • It cannot see non-code coupling. Two constants that must agree across two files, a Helm value a Python default mirrors, an API shape the SPA assumes — no call edge, no edge in the graph. That is precisely the class of bug in the second example above, and this skill would not have caught it either.
  • Green here is not green in CI. It reasons about the tree you have. Run kc-preflight.

© imran31415, MIT. 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 .claude/skills/kc-scope-pr of imran31415/kube-coder.

Open the folder on GitHubat commit fc0b886

Compare with similar skills

Kc Scope PR 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.

Kc Scope PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kc Scope PR this skillimran31415/kube-coder388—~1.2kAutomated safety check: NotesMIT
Adopt PR Branch Contextpydantic/pydantic-ai-harness952—~1.8kAutomated safety check: PassMIT
Compasscrabbuild/compass169—~5kAutomated safety check: PassCustom licence
Onboard Team Area in Databricks CLIdatabricks/cli404—~851Automated safety check: NotesCustom licence
Slm Graphqualixar/superlocalmemory231—~3kAutomated safety check: NotesAGPL-3.0
CodeScope Codebase Graph AnalysisQwenLM/qwen-code28k1 repos~9.3kAutomated safety check: PassApache-2.0

Similar skills

  • Adopt PR Branch Context

    pydantic/pydantic-ai-harness

    Official

    Fills in issue-brief.md and pr-decisions.md for an existing pull request, so you can pick up a PR mid-flight with its linked issue and past review decisions summarized.

    952 GitHub stars~1.8k tokensUpdated 6 days ago
    DevelopmentAuto-check passed

  • Compass

    crabbuild/compass

    A skill your agent uses for graph-first AI coding sessions and repository analysis: session initialization, architecture maps, dependency or call-graph tracing, symbol and repository search…

    169 GitHub stars~5k tokensUpdated 6 days ago
    DevelopmentAuto-check passed

  • Onboard Team Area in Databricks CLI

    databricks/cli

    Official

    Walks through reserving a directory for a team in the Databricks CLI repo and wiring GitHub CODEOWNERS so that team's approvals are required for its area.

    404 GitHub stars~851 tokensUpdated today
    DevelopmentAuto-check: notes

  • Slm Graph

    qualixar/superlocalmemory

    Index and query a codebase as a structural graph — build the code graph, trace blast radius of a change, find callers/callees/inheritors, semantic code search by meaning, assemble PR review context…

    231 GitHub stars~3k tokensUpdated today
    DevelopmentAuto-check: notes

  • CodeScope Codebase Graph Analysis

    QwenLM/qwen-code

    Answers questions about code structure, history, bugs and PR risk using a CodeScope knowledge graph and semantic index built from the repository.

    28k GitHub starsUsed in 1 repo~9.3k tokens
    DevelopmentAuto-check passed

  • Code Tour

    github/awesome-copilot

    Official

    A skill your agent uses to create CodeTour .tour files — persona-targeted, step-by-step walkthroughs that link to real files and line numbers.

    40k GitHub starsUsed in 1 repo~5.6k tokens
    DevelopmentAuto-check passed

More from imran31415/kube-coder

All 8 skills in this repo

  • Kc Entrypoint Change

    imran31415/kube-coder

    Safely edit the workspace pod's boot scripts (start.sh, the entrypoint/ssh-server configmaps) in kube-coder.

    388 GitHub stars~1.3k tokensUpdated today
    Auto-check: notes

  • Kc Issue

    imran31415/kube-coder

    Spin up an isolated agent to work a GitHub issue of kube-coder or any other repo checked out in the workspace.

    388 GitHub stars~1.9k tokensUpdated today
    Auto-check: notes

  • Kc Screenshot

    imran31415/kube-coder

    Capture desktop + mobile, dark + light screenshots of the kube-coder dashboard SPA for visual QA of a UI change.

    388 GitHub stars~870 tokensUpdated today
    Auto-check: notes

  • Kc Ship PR

    imran31415/kube-coder

    Commit local changes and open a pull request against kube-coder from inside a workspace pod.

    388 GitHub stars~2k tokensUpdated today
    Auto-check: notes

  • Remote Task

    imran31415/kube-coder

    Launch a Claude task on a remote kube-coder workspace, check task status, or attach to a running session.

    388 GitHub stars~1.3k tokensUpdated today
    Auto-check: notes

  • Kc Preflight

    imran31415/kube-coder

    Run kube-coder's full CI suite locally before pushing — helm lint + unit tests, server.py tests, dashboard + controller SPA builds + vitest, and shell syntax checks.

    388 GitHub stars~1k tokensUpdated today
    Auto-check: notes

Categories

Questions about Kc Scope PR

What does Kc Scope PR do?

Scope a kube-coder change before you open or update a PR — what the diff actually touches, which tests reach it, what the change made worse, and what is left untested. Kc Scope PR is an agent skill from imran31415/kube-coder. Scope a kube-coder change before you open or update a PR — what the diff actually touches, which tests reach it, what the change made worse, and what is left untested.

When should I use Kc Scope PR?

Kc Scope PR fits situations like: tasks that involve Codebase onboarding; tasks that involve Pull requests.

How do I install Kc Scope PR in Claude Code?

Run `npx skills add imran31415/kube-coder --skill kc-scope-pr -a claude-code`. Or copy the skill folder (.claude/skills/kc-scope-pr in imran31415/kube-coder) into .claude/skills/kc-scope-pr in your project. Claude Code loads it when a task matches its description.

How do I install Kc Scope PR in Codex?

Run `npx skills add imran31415/kube-coder --skill kc-scope-pr -a codex`. Or copy the skill folder (.claude/skills/kc-scope-pr in imran31415/kube-coder) into .agents/skills/kc-scope-pr in your project. Codex loads it when a task matches its description.

Can I use Kc Scope PR 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 imran31415/kube-coder --skill kc-scope-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kc-scope-pr, .gemini/skills/kc-scope-pr, .github/skills/kc-scope-pr and .opencode/skills/kc-scope-pr in your project.

What does Kc Scope PR need to run?

SKILL.md names no scripts, command-line tools or credentials: Kc Scope PR is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read.

Does Kc Scope PR 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 Kc Scope PR safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Kc Scope PR use?

Kc Scope PR is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kc Scope PR use?

About 1.2k tokens (SKILL.md is roughly 4.6k 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 Kc Scope PR?

Skills that share tags, products or a category with Kc Scope PR: Adopt PR Branch Context (pydantic/pydantic-ai-harness, 952 stars), Compass (crabbuild/compass, 169 stars), Onboard Team Area in Databricks CLI (databricks/cli, 404 stars) and Slm Graph (qualixar/superlocalmemory, 231 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kc Scope PR?

imran31415 (a GitHub user) maintains it in imran31415/kube-coder, which has 388 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 8, 2026.

Source: imran31415/kube-coder on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.