Phase transition rules and completion criteria for Forge 9-phase workflow
/plugin marketplace add chkim-su/forge/plugin install chkim-su-forge@chkim-su/forgeThis skill is limited to using the following tools:
This skill defines the 9-phase operational workflow and transition rules.
| Phase | Name | Strict | Completion Criteria |
|---|---|---|---|
| 0 | Input Normalization | YES | Intent captured, scope identified |
| 1 | Semantic Routing | no | Decision axes identified |
| 2 | Codebase Reality | no | Reality description complete |
| 3 | Mismatch Evaluation | no | Mismatch evaluated (skip if no mismatch) |
| 4 | Structured Questioning | YES | All questions answered |
| 5 | Option Synthesis | no | Options presented |
| 6 | Workflow Creation | no | Workflow defined or skipped |
| 7 | Execution | YES | User confirmation received, execution complete |
| 8 | Validation | no | All validations passed |
These phases block non-allowed tools:
These phases warn but do not block:
[0: Input Normalization] ──(intent captured)──> [1: Semantic Routing]
│
│ (STRICT: must complete before proceeding)
│
[1: Semantic Routing] ──(axes identified)──> [2: Codebase Reality]
│
[2: Codebase Reality] ──(description complete)──> [3: Mismatch Evaluation]
│
[3: Mismatch Evaluation] ─┬─(mismatch found)──> [4: Structured Questioning]
│
└─(no mismatch)──> [5: Option Synthesis]
│
[4: Structured Questioning] ──(answers received)──> [5: Option Synthesis]
│
│ (STRICT: must follow Dialogue Contract)
│
[5: Option Synthesis] ──(options presented)──> [6: Workflow Creation]
│
[6: Workflow Creation] ─┬─(workflow defined)──> [7: Execution]
│
└─(no workflow)──> [7: Execution]
│
[7: Execution] ──(user confirmation)──> [execution proceeds]
│
│ (STRICT: requires user confirmation)
│
[7: Execution] ──(execution complete)──> [8: Validation]
│
[8: Validation] ──(all passed)──> [COMPLETE]
When a workflow is confirmed in Phase 7:
workflow_version is set to 1If the workflow is modified:
workflow_version incrementsworkflow_confirmed resets to falseconfig/phase-definitions.yaml for machine-readable definitionsscripts/forge-daemon.py for state managementscripts/pretool-hook.py for enforcementThis 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 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 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.