From dstoic
Pre-gate self-check for drift detection and philosophy alignment. Use when: preparing for human gate review, checking implementation quality, or detecting scope drift.
npx claudepluginhub digital-stoic-org/agent-skills --plugin dstoicThis skill is limited to using the following tools:
Pre-gate self-check skill. Verifies acceptance criteria, detects scope drift, and ensures philosophy alignment before human review.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Pre-gate self-check skill. Verifies acceptance criteria, detects scope drift, and ensures philosophy alignment before human review.
flowchart LR
A["Read context"] --> B["Check criteria"]
B --> C["Detect drift"]
C --> D["Check philosophy"]
D --> E["Self-assess"]
E --> F["Generate report"]
classDef action fill:#E1BEE7,stroke:#7B1FA2,color:#000
class A,B,C,D,E,F action
Critical: Run before human gates. Catches drift BEFORE human reviews.
Run comprehensive pre-gate self-check.
Input: $ARGUMENTS = change-id
Workflow:
Load context:
openspec/changes/{change-id}/proposal.md for acceptance criteriaopenspec/changes/{change-id}/tasks.md for progressopenspec/changes/{change-id}/test.md for test strategy (if exists)openspec/changes/{change-id}/specs/*.md for requirementsopenspec/project.md for Execution PhilosophyPre-gate check (scale/maintenance mode only):
test.md existsCheck acceptance criteria:
Detect scope drift:
git status and git diff --stat to find actual changes(actual - proposed) / proposed * 100Check philosophy alignment:
mode from Execution PhilosophySelf-assessment:
Generate gate-ready report (see format below)
Autonomous (no confirmation needed):
Ask-first (pause and confirm):
Read openspec/project.md → Execution Philosophy → mode.
| Mode | Flag Anti-patterns |
|---|---|
garage | Over-engineering, premature abstraction, analysis paralysis |
scale | Cowboy coding, skipping tests, undocumented decisions |
maintenance | Refactoring for aesthetics, feature creep, risky upgrades |
Format: ⚠️ PHILOSOPHY VIOLATION ({mode}) - {anti-pattern}: {evidence}
# Reflection Report: {change-id}
## Test Strategy Coverage
- test.md: {present/missing}
- Mode: {mode}
{if missing + scale/maintenance: ⚠️ MISSING_TEST_MD - required for {mode} mode}
{if missing + garage: ℹ️ test.md optional in garage mode}
{if present: - Coverage: {summary of test.md sections}}
## Criteria Status
| Criterion | Status | Evidence |
|-----------|--------|----------|
| {criterion 1} | {met/unmet/partial} | {evidence} |
| {criterion 2} | {met/unmet/partial} | {evidence} |
## Scope Analysis
- Proposed files: {n}
- Actual files: {m}
- Deviation: {percent}%
{if >20%: ⚠️ SCOPE DRIFT DETECTED - requires human review}
## Philosophy Alignment
- Mode: {mode}
- Anti-patterns detected: {list or "None"}
{if violations: ⚠️ PHILOSOPHY VIOLATION - {details}}
## Self-Assessment
**Question**: Am I solving the right problem?
**Answer**: {assessment based on proposal's Problem statement}
## Deviations Requiring Attention
{list with ⚠️ emoji for each, or "None"}
## Recommendation
{READY FOR GATE | NOT READY - {reasons}}
MISSING_TEST_MD - test.md missing in scale/maintenance modeSCOPE_DRIFT - Files changed exceed proposal by >20%CRITERIA_UNMET - Acceptance criterion not satisfiedPHILOSOPHY_VIOLATION - Anti-pattern for current modeSPEC_DEVIATION - Implementation differs from specsFormat: ⚠️ DEVIATION: {type} - Expected: {X}, Actual: {Y}, Impact: {Z}, Rec: {action}
See reference.md for detailed examples and patterns.