Borrowing it
Nothing to install: this file belongs to go-to-k/cdkd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/go-to-k/cdkd/main/.claude/skills/verify-pr/SKILL.mdgit clone --depth 1 https://github.com/go-to-k/cdkdWrote 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.
[](https://agentmods.dev/skills/go-to-k/cdkd/verify-pr)<a href="https://agentmods.dev/skills/go-to-k/cdkd/verify-pr"><img src="https://agentmods.dev/badge/skills/go-to-k/cdkd/verify-pr.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 132 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00029 | $0.05331 |
| Opus 5 | $0.00015 | $0.02665 |
| Sonnet 5 | $0.00006 | $0.01066 |
| Haiku 4.5 | $0.00003 | $0.00533 |
Grade A, and why
verify-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Readiness Verification
Heavy pre-merge gate. Run before creating or merging a pull request — NOT
before every commit (per-commit verification is /check, enforced by the
check-gate hook).
Checklist
Run each check and report pass/fail:
-
Worktree pre-flight:
[ -d node_modules ] || pnpm install.git worktree adddoes NOT copynode_modules, so a fresh worktree's typecheck/lint/build/test all fail withtsc: command not foundetc. — and the failure is easy to miss when output is piped totail(the exit code reflectstail). If skipping via an existingnode_modules, spot-checkpnpm-lock.yamlmtime ≤node_modules/.modules.yamlmtime. Do not start step 1 until this passes, or every check below silently no-ops. -
Code quality
vp run typecheck,vp run lint(lint:fixfirst if needed),vp run buildall pass.- When piping to
tail/head/grep, check the output content forError/Command failed—$?after a pipeline reflects the LAST stage, and a background-task notification'sexit code 0is the chained command's exit. When in doubt:vp run X > /tmp/out 2>&1; rc=$?; tail -3 /tmp/out; echo "[rc=$rc]".
-
Tests
vp test run— all unit tests pass. Preferred overvp run test: nothing sits between the caller and the verdict (/checkstep 4 has the full rationale). Report test count.- Every scope / diff check in this skill uses
origin/main...HEAD, nevermain...HEAD— the gate hooks derive scope fromorigin/main, so an unfetched localmainmakes this skill and the merge-blocking hook disagree about what the branch touched. - Test coverage check: compare the diff's
src/changes vstests/changes; new/modified logic with no corresponding test update = fail — add the missing tests before proceeding.
-
CI status
- PR number: argument, else
gh pr view --json number -q .number, else ask viaAskUserQuestion. - FIRST:
gh pr view <PR> --json mergeStateStatus,mergeable -q '"mergeable=\(.mergeable) state=\(.mergeStateStatus)"'— atmergeable=CONFLICTING state=DIRTYthe CI workflow NEVER fires, however long you wait (PR #404: ~70 min lost; close+reopen and force-pushing unchanged content do not re-trigger). Resolution:git fetch origin main && git rebase origin/main, resolve, force-push — CI fires within ~30s. - Only after the state is
CLEAN/UNSTABLE/BLOCKED/BEHIND:gh pr checks <PR>— all pass; if pending, wait and recheck.
- PR number: argument, else
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.
- today Changed · +1 lines b8d4163ba20c
- yesterday Changed · +4 lines d0c87b7f0ccb
- 4d ago Changed · +59 lines 3e8e30308f3e
- 5d ago Changed 650e9b274d08
- 8d ago First seen · 321 lines · 29 tokens per session scan A 3dc1071516ca
verify-pr is a skill published in the GitHub repository go-to-k/cdkd (135 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 5,331 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
aws-cdk-mcp-server-mcp
AWS Cloud Development Kit (CDK) best practices, infrastructure as code patterns, and security compliance with CDK Nag.
aws-testing
Testing strategies for AWS workloads. Use when writing unit tests, integration tests, contract tests, mocking AWS services, or setting up quality gates and CI/CD test pipelines.
python-runtime
Python toolchain configuration and best practices. Use when setting up Ruff, pytest, mypy type hints, dependency management, virtual environments or Python project standards.
prowler-pr
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml…
prowler-test-api
Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.