declare-cc 1.0.8 → 2.0.0

package/commands/declare/debug.md

@@ -1,162 +0,0 @@
----
-name: declare:debug
-description: Systematic debugging with persistent state across context resets
-argument-hint: "[issue description]"
-allowed-tools:
-  - Read
-  - Bash
-  - Task
-  - AskUserQuestion
----
-
-<objective>
-Debug issues using scientific method with subagent isolation.
-
-**Orchestrator role:** Gather symptoms, spawn declare-debugger agent, handle checkpoints, spawn continuations.
-
-**Why subagent:** Investigation burns context fast (reading files, forming hypotheses, testing). Fresh context per investigation. Main context stays lean for user interaction.
-</objective>
-
-<context>
-User's issue: $ARGUMENTS
-
-Check for active sessions:
-```bash
-ls .planning/debug/*.md 2>/dev/null | grep -v resolved | head -5
-```
-</context>
-
-<process>
-
-## 0. Initialize Context
-
-```bash
-INIT=$(node dist/declare-tools.cjs get-state)
-```
-
-Extract `commit_docs` from init JSON. Resolve debugger model:
-```bash
-DEBUGGER_MODEL=$(node dist/declare-tools.cjs config-get debugger_model 2>/dev/null || echo "claude-opus-4-5")
-```
-
-## 1. Check Active Sessions
-
-If active sessions exist AND no $ARGUMENTS:
-- List sessions with status, hypothesis, next action
-- User picks number to resume OR describes new issue
-
-If $ARGUMENTS provided OR user describes new issue:
-- Continue to symptom gathering
-
-## 2. Gather Symptoms (if new issue)
-
-Use AskUserQuestion for each:
-
-1. **Expected behavior** - What should happen?
-2. **Actual behavior** - What happens instead?
-3. **Error messages** - Any errors? (paste or describe)
-4. **Timeline** - When did this start? Ever worked?
-5. **Reproduction** - How do you trigger it?
-
-After all gathered, confirm ready to investigate.
-
-## 3. Spawn declare-debugger Agent
-
-Fill prompt and spawn:
-
-```markdown
-<objective>
-Investigate issue: {slug}
-
-**Summary:** {trigger}
-</objective>
-
-<symptoms>
-expected: {expected}
-actual: {actual}
-errors: {errors}
-reproduction: {reproduction}
-timeline: {timeline}
-</symptoms>
-
-<mode>
-symptoms_prefilled: true
-goal: find_and_fix
-</mode>
-
-<debug_file>
-Create: .planning/debug/{slug}.md
-</debug_file>
-```
-
-```
-Task(
-  prompt=filled_prompt,
-  subagent_type="declare-debugger",
-  model="{debugger_model}",
-  description="Debug {slug}"
-)
-```
-
-## 4. Handle Agent Return
-
-**If `## ROOT CAUSE FOUND`:**
-- Display root cause and evidence summary
-- Offer options:
-  - "Fix now" - spawn fix subagent
-  - "Plan fix" - suggest `/declare:plan` to address root cause
-  - "Manual fix" - done
-
-**If `## CHECKPOINT REACHED`:**
-- Present checkpoint details to user
-- Get user response
-- Spawn continuation agent (see step 5)
-
-**If `## INVESTIGATION INCONCLUSIVE`:**
-- Show what was checked and eliminated
-- Offer options:
-  - "Continue investigating" - spawn new agent with additional context
-  - "Manual investigation" - done
-  - "Add more context" - gather more symptoms, spawn again
-
-## 5. Spawn Continuation Agent (After Checkpoint)
-
-When user responds to checkpoint, spawn fresh agent:
-
-```markdown
-<objective>
-Continue debugging {slug}. Evidence is in the debug file.
-</objective>
-
-<prior_state>
-Debug file: @.planning/debug/{slug}.md
-</prior_state>
-
-<checkpoint_response>
-**Type:** {checkpoint_type}
-**Response:** {user_response}
-</checkpoint_response>
-
-<mode>
-goal: find_and_fix
-</mode>
-```
-
-```
-Task(
-  prompt=continuation_prompt,
-  subagent_type="declare-debugger",
-  model="{debugger_model}",
-  description="Continue debug {slug}"
-)
-```
-
-</process>
-
-<success_criteria>
-- [ ] Active sessions checked
-- [ ] Symptoms gathered (if new)
-- [ ] declare-debugger spawned with context
-- [ ] Checkpoints handled correctly
-- [ ] Root cause confirmed before fixing
-</success_criteria>

package/commands/declare/discuss.md

@@ -1,65 +0,0 @@
----
-description: Gather milestone context through adaptive questioning before execution
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
-  - Grep
-  - AskUserQuestion
-  - Task
-argument-hint: "<M-XX> [--auto]"
----
-
-Extract implementation decisions that downstream agents need — the planner and executor will use CONTEXT.md to know what choices are locked.
-
-**How it works:**
-1. Analyze the milestone to identify gray areas (behavior, output, flow, etc.)
-2. Present gray areas — user selects which to discuss
-3. Deep-dive each selected area until satisfied
-4. Create CONTEXT.md with decisions that guide planning and execution
-
-**Output:** `CONTEXT.md` in the milestone folder — decisions clear enough that downstream agents can act without asking the user again.
-
-**Step 1: Load the graph.**
-
-```bash
-node dist/declare-tools.cjs load-graph
-```
-
-Parse the JSON output. If it contains an `error` field, tell the user to run `/declare:init` first and stop.
-
-Extract milestone data. Identify the milestone matching `$ARGUMENTS` (e.g., `M-01`). If no milestone ID is provided, tell the user to provide one (e.g., `/declare:discuss M-01`) and stop.
-
-If the milestone ID is not found in the graph, tell the user and stop:
-```
-Milestone [M-XX] not found.
-
-Use /declare:status to see available milestones.
-```
-
-**Step 2: Follow the discuss workflow.**
-
-Read and follow all steps in:
-
-@workflows/discuss.md
-
-Pass the loaded graph state and milestone data into the workflow.
-
-The milestone directory is: `.planning/milestones/[M-XX]-[slug]/`
-
-CONTEXT.md is written to: `.planning/milestones/[M-XX]-[slug]/CONTEXT.md`
-
-**Step 3: Commit context.**
-
-After CONTEXT.md is written, commit it:
-
-```bash
-node dist/declare-tools.cjs commit "docs(M-XX): capture milestone context" --files ".planning/milestones/[M-XX]-[slug]/CONTEXT.md"
-```
-
-Replace `M-XX` and `[M-XX]-[slug]` with the actual milestone ID and slug.
-
-**Step 4: Handle auto-advance.**
-
-Check for `--auto` in `$ARGUMENTS` and follow the auto-advance step in the workflow.