gstredny/plan-review
scaffold/.codex/skills/plan-review/SKILL.md
Review an implementation plan before execution to catch missed success criteria, scope creep, constraint violations, unverified assumptions, and missed reuse opportunities.
$ install --global
skillsauthnpx skillsauth add gstredny/lauren-loop plan-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 3:32 PM13.2s1 file scanned
SKILL.md
- name:
- plan-review
- description:
- Review an implementation plan before execution to catch missed success criteria, scope creep, constraint violations, unverified assumptions, and missed reuse opportunities.
Plan Review
Use this skill after a plan exists and before code is written.
Checklist
- Does the plan cover every success criterion from the task file?
- Does the plan respect repo-level constraints from project rules and task-specific rules?
- Is there a simpler approach that reaches the same outcome with fewer new abstractions or files?
- Are all important assumptions verified by reading code, configs, or docs already in the repo?
- Does the plan stay within the intended scope and file set?
- Does it reuse existing helpers, services, tests, and patterns instead of duplicating them?
- Does the plan name the public interface under test for each behavior?
- Does it allow mocks only at true external boundaries and keep internal collaborators real?
- Does it sequence the work as one-test, one-implementation vertical slices instead of bulk upfront test writing?
- Are non-testable steps explicitly marked as verification-only work instead of forced into fake TDD?
Decision Rules
- If items 1, 2, 4, 7, or 8 fail, stop and resolve the gap before execution.
- If items 3, 5, 6, 9, or 10 fail, simplify the plan and re-check it.
- Prefer the smallest plan that still satisfies the task and verification requirements.
Related Skills
gstredny/workflow
development
VerifiedTrustedCommunity
Follow the end-to-end delivery workflow for planning, task-file management, execution, code review, verification, and closeout without relying on Claude-specific hooks or command conventions.
1SKILL.mdUpdated Apr 5, 2026
gstredny/tdd-planning
testing
VerifiedTrustedCommunity
Plan implementation work before coding by defining public interfaces, real collaborator boundaries, and vertical RED or VERIFY slices.
1SKILL.mdUpdated Apr 5, 2026
gstredny/task-manager
development
VerifiedTrustedCommunity
Manage task files in docs/tasks/open and docs/tasks/closed, including task discovery, resume/create rules, append-only Attempts logging, Left Off At updates, Code Review field handling, and needs verification closeout.
1SKILL.mdUpdated Apr 5, 2026
gstredny/code-review
development
VerifiedTrustedCommunity
Run code review with findings-first, severity-ordered output focused on bugs, regressions, edge cases, error handling, performance, architecture, caller impact, and missing tests.
1SKILL.mdUpdated Apr 5, 2026