Track and document all decisions made by agents, providing transparency into what was decided, why, and what alternatives were considered.
/plugin marketplace add marcel-Ngan/ai-dev-team/plugin install marcel-ngan-ai-dev-team@marcel-Ngan/ai-dev-teamThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Track and document all decisions made by agents, providing transparency into what was decided, why, and what alternatives were considered.
| Category | Authority | Examples |
|---|---|---|
| Requirements | BA, PO | Story scope, acceptance criteria |
| Priority | PO | Sprint inclusion, MoSCoW |
| Technical | Architect, Sr Dev | Architecture, patterns, tools |
| Process | Orchestrator, EM | Workflow routing, ceremonies |
| Quality | QA | Test strategy, coverage targets |
| Deployment | DevOps | Environment, timing, rollback |
| Escalated | Stakeholder | Scope, budget, timeline |
| Level | Criteria | Retention |
|---|---|---|
| Critical | Irreversible, high impact | Permanent |
| Major | Significant scope/direction | 2 years |
| Standard | Normal workflow decisions | 1 year |
| Minor | Low impact, easily changed | 90 days |
interface DecisionRecord {
// Identity
id: string; // DEC-XXX format
timestamp: string; // When decided
session_id: string; // Workflow session
// Classification
category: DecisionCategory; // requirements, technical, etc.
significance: Significance; // critical, major, standard, minor
// Decision Maker
agent: string; // Agent that made decision
delegated_by?: string; // If authority was delegated
stakeholder_input?: boolean; // Required stakeholder input
// Decision Content
decision_point: string; // What needed to be decided
context: string; // Background and constraints
options: Array<{
name: string;
description: string;
pros: string[];
cons: string[];
rejected_reason?: string;
}>;
selected_option: string; // Which option was chosen
rationale: string; // Why this option
// Impact
impact: {
artifacts_created?: string[];
artifacts_modified?: string[];
constraints_added?: string[];
dependencies?: string[];
};
// Traceability
related_tickets: string[]; // Jira tickets
related_decisions: string[]; // Other decisions
related_docs: string[]; // Confluence pages
// Reversibility
reversible: boolean;
reversal_cost?: string; // If reversible, what's the cost
}
## Decision: {{id}}
**Date:** {{date}}
**Agent:** {{agent}}
**Category:** {{category}}
**Question:** {{decision_point}}
**Decision:** {{selected_option}}
**Why:** {{rationale}}
**Impact:** {{impact_summary}}
## Decision Record: {{id}}
### Metadata
| Field | Value |
|-------|-------|
| Date | {{timestamp}} |
| Agent | {{agent}} |
| Category | {{category}} |
| Significance | {{significance}} |
| Workflow | {{workflow}} |
### Context
{{context_description}}
**Constraints:**
{{constraints}}
**Stakeholders:**
{{stakeholders}}
---
### Decision Point
{{decision_point}}
---
### Options Considered
#### Option 1: {{option_1_name}}
{{option_1_description}}
| Pros | Cons |
|------|------|
{{option_1_pros_cons}}
#### Option 2: {{option_2_name}}
{{option_2_description}}
| Pros | Cons |
|------|------|
{{option_2_pros_cons}}
#### Option 3: {{option_3_name}}
{{option_3_description}}
| Pros | Cons |
|------|------|
{{option_3_pros_cons}}
---
### Decision
**Selected:** {{selected_option}}
**Rationale:**
{{rationale}}
**Trade-offs Accepted:**
{{tradeoffs}}
---
### Impact
**Artifacts Created:**
{{created_artifacts}}
**Artifacts Modified:**
{{modified_artifacts}}
**Constraints Added:**
{{new_constraints}}
**Dependencies:**
{{dependencies}}
---
### Reversibility
**Reversible:** {{reversible}}
**Reversal Cost:** {{reversal_cost}}
**Point of No Return:** {{point_of_no_return}}
---
### Related
**Tickets:** {{related_tickets}}
**Decisions:** {{related_decisions}}
**Documentation:** {{related_docs}}
## Pending Decisions
Decisions awaiting stakeholder input:
| ID | Question | Agent | Waiting Since | Blocker |
|----|----------|-------|---------------|---------|
{{pending_decisions}}
### Actions Needed
{{action_items}}
## Recent Decisions
### Last 24 Hours
| ID | Decision | Agent | Category | Impact |
|----|----------|-------|----------|--------|
{{recent_decisions}}
### Decision Statistics
- Total: {{total}}
- By Agent: {{by_agent}}
- By Category: {{by_category}}
## Decisions for {{ticket_id}}
### Decision Trail
{{decision_timeline}}
### Key Decisions
1. **{{decision_1}}** - {{agent_1}} - {{date_1}}
{{summary_1}}
2. **{{decision_2}}** - {{agent_2}} - {{date_2}}
{{summary_2}}
### Impact Summary
{{total_impact}}
# Decision Log - {{project_name}}
## {{current_month}}
### Week of {{week_start}}
| ID | Date | Decision | Agent | Category | Impact |
|----|------|----------|-------|----------|--------|
{{weekly_decisions}}
---
## Decision Index
### By Category
- [Requirements Decisions](#requirements)
- [Technical Decisions](#technical)
- [Priority Decisions](#priority)
### By Significance
- [Critical Decisions](#critical)
- [Major Decisions](#major)
observability-activity-log - Activity trackingconfluence-decision-log - Decision documentationgeneration-adr - Architecture decisionsAtlassian:createConfluencePage - Decision log pagesAtlassian:updateConfluencePage - Update logsAtlassian:addCommentToJiraIssue - Decision on ticketsThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.