A skill that examines a code change's likely impact before a pull request, including affected code, reachable tests, regressions, and untested areas.

It is for scoping pull requests, finding tests affected through the call graph, and identifying work that still lacks coverage.

It reduces the risk of underestimating a change because the edited files do not show every dependent component or relevant test.

How imran31415/kube-coder configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to imran31415/kube-coder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/imran31415/kube-coder/main/.claude/skills/kc-scope-pr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/imran31415/kube-coder

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/imran31415/kube-coder/kc-scope-pr/github.svg)](https://agentmods.dev/skills/imran31415/kube-coder/kc-scope-pr)

Your own site

<a href="https://agentmods.dev/skills/imran31415/kube-coder/kc-scope-pr"><img src="https://agentmods.dev/badge/skills/imran31415/kube-coder/kc-scope-pr/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/imran31415/kube-coder/kc-scope-pr"><img src="https://agentmods.dev/badge/skills/imran31415/kube-coder/kc-scope-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,189 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00102	$0.01189
Opus 5.5	$0.00041	$0.00476
Sonnet 5.5	$0.00020	$0.00238
Haiku 4.5	$0.00010	$0.00119

Measured 1mo ago against content hash ec6a95af61c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kc-scope-pr 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 1mo 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.

.claude/skills/kc-scope-pr/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

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:

Read the full file on GitHub · 101 lines

Changes

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.

1mo ago First seen · 101 lines · 102 tokens per session scan A ec6a95af61c8

Subscribe to this mod's changes

kc-scope-pr is a skill published in the GitHub repository imran31415/kube-coder (399 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 1,189 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-08.

Code review Testing

kc-scope-pr next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kc-scope-primran31415/kube-coder	Skill	399	2d ago	MIT	A	102	Claude Code
autoreviewopenclaw/clawhub	Skill	9.5k	yesterday	MIT	A	17	Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills	Skill	2.2k	5d ago	MIT	A	115	Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermes	Skill	5.2k	yesterday	MIT	A	48	Claude Code, Codex
revdiff-planumputun/revdiff	Skill	945	yesterday	MIT	A	84	Claude Code
explore-unknownsdzhng/skills	Skill	1.4k	2d ago	MIT	A	162	Claude Code, Codex
re0-mergeLilMGenius/paperthin	Skill	1.4k	4d ago	MIT	A	70	Claude Code

kube-coder: Skill for Claude Code