Workflow methodologies for analysis, evidence gathering, and structured output.
Imbue provides reusable patterns for approaching analysis tasks. It’s a methodology plugin - the patterns apply to various inputs (git diffs, specs, logs) and chain together for complex workflows.
Core Philosophy : “NO IMPLEMENTATION WITHOUT A FAILING TEST FIRST” - The Iron Law enforced through proof-of-work validation.
/plugin install imbue@claude-night-market
Generalizable : Patterns work across different input typesComposable : Skills chain together naturallyEvidence-based : Emphasizes capturing proof for reproducibilityTDD-First : Iron Law enforcement prevents cargo cult testing
Skill Description When to Use
review-coreScaffolding for detailed reviews Starting architecture, security, or code quality reviews evidence-loggingEvidence capture methodology Creating audit trails during analysis structured-outputOutput formatting patterns Preparing final reports
Skill Description When to Use
diff-analysisSemantic changeset analysis Understanding impact of changes catchupContext recovery Getting up to speed after time away
Skill Description When to Use
scope-guardAnti-overengineering Evaluating if features should be built now proof-of-workEvidence-based validation Enforcing Iron Law TDD discipline rigorous-reasoningAnti-sycophancy guardrails Analyzing conflicts, evaluating contested claims
Skill Description When to Use
feature-reviewFeature prioritization Sprint planning, roadmap reviews
Skill Description When to Use
workflow-monitorExecution monitoring and issue creation After workflow failures or inefficiencies
Command Description
/catchupQuick context recovery from recent changes /structured-reviewStart structured review workflow with evidence logging /feature-reviewFeature prioritization with RICE+WSJF scoring
Agent Description
review-analystAutonomous structured reviews with evidence gathering
Hook Type Description
session-start.shSessionStart Initializes scope-guard, Iron Law, and learning mode user-prompt-submit.shUserPromptSubmit Validates prompts against scope thresholds tdd_bdd_gate.pyPreToolUse Enforces Iron Law at write-time pre-pr-scope-check.shManual Checks scope before PR creation proof-enforcement.mdDesign Iron Law TDD compliance enforcement
Skill(imbue:review-core)
# Required TodoWrite items:
# 1. review-core:context-established
# 2. review-core:scope-inventoried
# 3. review-core:evidence-captured
# 4. review-core:deliverables-structured
# 5. review-core:contingencies-documented
Skill(imbue:diff-analysis)
# Answers: "What changed and why does it matter?"
# - Categorizes changes by function
# - Assesses risks
# - Summarizes implications
/catchup
# Summarizes:
# - Recent commits
# - Changed files
# - Key decisions
# - Action items
/feature-review
# Uses hybrid RICE+WSJF scoring:
# - Reach, Impact, Confidence, Effort
# - Weighted Shortest Job First
# - ISO 25010 quality dimensions
The scope-guard skill prevents overengineering via four components:
Component Purpose
decision-frameworkWorthiness formula and scoring anti-overengineeringRules to prevent scope creep branch-managementThreshold monitoring (lines, commits, days) baseline-scenariosValidated test scenarios
The proof-of-work skill enforces the Iron Law :
NO IMPLEMENTATION WITHOUT A FAILING TEST FIRST
This prevents “Cargo Cult TDD” where tests validate pre-conceived implementations.
Thought Pattern Violation Action
“Let me plan the implementation first” Skipping RED Write failing test FIRST “I know what tests we need” Pre-conceived impl Document failure, THEN design “The design is straightforward” Skipping uncertainty Let design EMERGE from tests
proof:iron-law-red - Failing test documented
proof:iron-law-green - Minimal code to pass
proof:iron-law-refactor - Code improved, tests green
proof:iron-law-coverage - Coverage gates verified
See iron-law-enforcement.md module for full enforcement patterns.
The rigorous-reasoning skill prevents sycophantic patterns through structured analysis:
Component Purpose
priority-signalsOverride principles (no courtesy agreement, checklist over intuition) conflict-analysisHarm/rights checklist for interpersonal conflicts debate-methodologyTruth claims and contested territory handling red-flag monitoringDetect sycophantic thought patterns
Thought Pattern Reality Check Action
“I agree that…” Did you validate? Apply harm/rights checklist “You’re right that…” Is this proven? Check for evidence “That’s a fair point” Fair by what standard? Specify the standard
All skills output TodoWrite items for progress tracking:
review-core:context-established
review-core:scope-inventoried
diff-analysis:baseline-established
diff-analysis:changes-categorized
catchup:context-confirmed
catchup:delta-captured
Imbue is foundational - other plugins build on it:
# Sanctum uses imbue for review patterns
Skill(imbue:review-core)
Skill(sanctum:git-workspace-review)
# Pensive uses imbue for evidence gathering
Skill(imbue:evidence-logging)
Skill(pensive:architecture-review)
Skill Enhancement
scope-guardUses brainstorming, writing-plans, execute-plan /feature-reviewUses brainstorming for feature suggestions
sanctum : Uses imbue for review scaffoldingpensive : Uses imbue for evidence gatheringspec-kit : Uses imbue for analysis patterns