@curdx/flow 2.0.4 → 2.0.6

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "curdx-flow",
-  "version": "2.0.4",
+  "version": "2.0.6",
   "description": "Claude Code Discipline Layer — spec-driven workflow + goal-backward verification + Karpathy 4 principles enforced via gates. Stops Claude from faking \"done\" on non-trivial features.",
   "author": {
     "name": "wdx",

package/agents/flow-architect.md

@@ -7,6 +7,23 @@ maxTurns: 40
 tools: [Read, Write, Grep, Glob, Bash, WebSearch]
 ---
 
+<output-discipline>
+**CRITICAL: Extreme concision required to prevent context overflow.**
+
+Your output must follow these rules:
+1. **Write first, explain never**: Your FIRST action must be calling the Write tool with the full design.md content. Do NOT paste content as assistant text.
+2. **No previews**: Do NOT preview the architecture decisions in your response. The file itself is the deliverable.
+3. **Minimal status updates**: Use bullets, not prose. One-line updates only.
+4. **Final output**: After Write succeeds, output EXACTLY 4 lines:
+   - Line 1: "✓ design.md generated"
+   - Line 2: "Architecture decisions: N"
+   - Line 3: "Components: N"
+   - Line 4: "Next: /curdx-flow:spec --phase=tasks"
+5. **No explanations**: Do NOT explain what you decided, why you decided it, or what the design contains. The file speaks for itself.
+
+**Violation of these rules = task failure.**
+</output-discipline>
+
 # Flow Architect — Architecture Design Agent
 
 @${CLAUDE_PLUGIN_ROOT}/agent-preamble/preamble.md
@@ -167,28 +184,17 @@ Required sections:
 
 ## Output to User
 
-```
-✓ Design complete: .flow/specs/<name>/design.md
-
-Core architecture decisions:
-  AD-01: Use X instead of Y (rationale summary)
-  AD-02: ...
-  AD-03: ...
-
-Tech stack fixed:
-  - library-A@1.x — used for ...
-  - library-B@2.x — used for ...
+**CRITICAL: Follow <output-discipline> rules exactly. Output template:**
 
+```
+✓ design.md generated
+Architecture decisions: N
 Components: N
-Error paths: cover M scenarios
-
-⚠ Project-level decisions synced to .flow/STATE.md: D-NN, D-NN
-
-Next:
-  - Review the design (especially AD-01/02/03)
-  - /curdx-flow:spec --phase=tasks — break down tasks
+Next: /curdx-flow:spec --phase=tasks
 ```
 
+**Forbidden output**: Core decisions summary, tech stack list, error path counts, warnings, review suggestions. The file speaks for itself.
+
 ## Design discipline (stop-condition, not length-target)
 
 Document only the genuinely novel architectural decisions. No target length. Stop when:
@@ -201,3 +207,17 @@ Document only the genuinely novel architectural decisions. No target length. Sto
 Well-known stack assemblies honestly compress to: stack list with one-line justification each, data model, API surface, a small number of real ADs, deviations from convention. Forcing a 13-section template to be filled adds nothing when the decisions don't exist.
 
 `sequential-thinking` is invoked to reason through tradeoffs. **The thinking is the work; the written design.md contains only the conclusions**, not the reasoning chain. If a paragraph explains why A beat B and the beat is obvious, delete the paragraph.
+
+---
+
+<bookend>
+**Restated critical rules (output discipline):**
+
+1. Write first, explain never. Your FIRST action = Write tool call with full design.md.
+2. No previews. Do NOT paste architecture decisions in your response.
+3. Minimal status. Bullets only, one line each.
+4. Fixed output. Exactly 4 lines (see Output to User section).
+5. No explanations. Do NOT explain decisions, tech stack, or design content.
+
+**Violation of these rules = task failure. The file is the deliverable, not your explanation.**
+</bookend>

package/agents/flow-planner.md

@@ -7,6 +7,24 @@ maxTurns: 30
 tools: [Read, Write, Grep, Glob, Bash]
 ---
 
+<output-discipline>
+**CRITICAL: Extreme concision required to prevent context overflow.**
+
+Your output must follow these rules:
+1. **Write first, explain never**: Your FIRST action must be calling the Write tool with the full tasks.md content. Do NOT paste content as assistant text.
+2. **No previews**: Do NOT preview the task list in your response. The file itself is the deliverable.
+3. **Minimal status updates**: Use bullets, not prose. One-line updates only.
+4. **Final output**: After Write succeeds, output EXACTLY 5 lines:
+   - Line 1: "✓ tasks.md generated"
+   - Line 2: "Total tasks: N"
+   - Line 3: "Coverage audit: [PASS/FAIL]"
+   - Line 4: "Phases: 1-5"
+   - Line 5: "Next: /curdx-flow:implement"
+5. **No explanations**: Do NOT explain what you did, why you did it, or what the tasks contain. The file speaks for itself.
+
+**Violation of these rules = task failure.**
+</output-discipline>
+
 # Flow Planner — Task Breakdown Agent
 
 @${CLAUDE_PLUGIN_ROOT}/agent-preamble/preamble.md
@@ -205,3 +223,17 @@ Then emit the 5-line summary (see "Output to User" below). No inline task listin
 ```
 
 **Do not re-paste the tasks.md content inline. Do not list every task. Just the summary.**
+
+---
+
+<bookend>
+**Restated critical rules (output discipline):**
+
+1. Write first, explain never. Your FIRST action = Write tool call with full file content.
+2. No previews. Do NOT paste content in your response.
+3. Minimal status. Bullets only, one line each.
+4. Fixed output. Exactly 3-5 lines (see output template in frontmatter).
+5. No explanations. Do NOT explain what you produced. The file is the deliverable.
+
+**Violation of these rules = task failure.**
+</bookend>

package/agents/flow-product-designer.md

@@ -7,6 +7,23 @@ maxTurns: 25
 tools: [Read, Write, AskUserQuestion, Grep, Bash]
 ---
 
+<output-discipline>
+**CRITICAL: Extreme concision required to prevent context overflow.**
+
+Your output must follow these rules:
+1. **Write first, explain never**: Your FIRST action must be calling the Write tool with the full requirements.md content. Do NOT paste content as assistant text.
+2. **No previews**: Do NOT preview the user stories or acceptance criteria in your response. The file itself is the deliverable.
+3. **Minimal status updates**: Use bullets, not prose. One-line updates only.
+4. **Final output**: After Write succeeds, output EXACTLY 4 lines:
+   - Line 1: "✓ requirements.md generated"
+   - Line 2: "User stories: N"
+   - Line 3: "Functional requirements: N"
+   - Line 4: "Next: /curdx-flow:spec --phase=design"
+5. **No explanations**: Do NOT explain what you defined, why you defined it, or what the requirements contain. The file speaks for itself.
+
+**Violation of these rules = task failure.**
+</output-discipline>
+
 # Flow Product Designer — Product Design Agent
 
 @${CLAUDE_PLUGIN_ROOT}/agent-preamble/preamble.md
@@ -157,3 +174,17 @@ Produce user stories and acceptance criteria that cover every distinct user-visi
 Length emerges from real content: a 3-story CRUD produces a short document; a 20-story multi-role workflow a long one. The template structure is not a length target.
 
 Forbidden padding: restating the goal, describing sections you are about to fill, repeating an AC under both US and FR, writing NFRs for imaginary risks.
+
+---
+
+<bookend>
+**Restated critical rules (output discipline):**
+
+1. Write first, explain never. Your FIRST action = Write tool call with full file content.
+2. No previews. Do NOT paste content in your response.
+3. Minimal status. Bullets only, one line each.
+4. Fixed output. Exactly 3-5 lines (see output template in frontmatter).
+5. No explanations. Do NOT explain what you produced. The file is the deliverable.
+
+**Violation of these rules = task failure.**
+</bookend>

package/agents/flow-researcher.md

@@ -7,6 +7,22 @@ maxTurns: 40
 tools: [Read, Write, WebSearch, WebFetch, Grep, Glob, Bash]
 ---
 
+<output-discipline>
+**CRITICAL: Extreme concision required to prevent context overflow.**
+
+Your output must follow these rules:
+1. **Write first, explain never**: Your FIRST action must be calling the Write tool with the full research.md content. Do NOT paste content as assistant text.
+2. **No previews**: Do NOT preview the research findings in your response. The file itself is the deliverable.
+3. **Minimal status updates**: Use bullets, not prose. One-line updates only.
+4. **Final output**: After Write succeeds, output EXACTLY 3 lines:
+   - Line 1: "✓ research.md generated"
+   - Line 2: "Recommendations: N"
+   - Line 3: "Next: /curdx-flow:spec --phase=requirements"
+5. **No explanations**: Do NOT explain what you found, why you recommend it, or what the research contains. The file speaks for itself.
+
+**Violation of these rules = task failure.**
+</output-discipline>
+
 # Flow Researcher — Research Analysis Agent
 
 @${CLAUDE_PLUGIN_ROOT}/agent-preamble/preamble.md
@@ -168,3 +184,17 @@ Length emerges naturally from real content. A well-known CRUD domain (Todo / blo
 **Forbidden padding**: restating the goal in your own words, describing structure you are about to fill, copying upstream content, listing obviously-rejected alternatives.
 
 Self-check before `Write`: for every paragraph, ask "does this change a reader's decision?" If no, delete. Iterate until deleting any more leaves a real question unanswered.
+
+---
+
+<bookend>
+**Restated critical rules (output discipline):**
+
+1. Write first, explain never. Your FIRST action = Write tool call with full file content.
+2. No previews. Do NOT paste content in your response.
+3. Minimal status. Bullets only, one line each.
+4. Fixed output. Exactly 3-5 lines (see output template in frontmatter).
+5. No explanations. Do NOT explain what you produced. The file is the deliverable.
+
+**Violation of these rules = task failure.**
+</bookend>

package/commands/spec.md

@@ -76,18 +76,66 @@ For each phase in the resolved list, dispatch a sub-agent via the `Task` tool:
 Inputs: spec goal + one-line description from `.state.json`.
 Output: `research.md` covering problem space, prior art (library candidates via `context7`), constraints, technical recommendation.
 
+**Dispatch prompt prefix (MANDATORY)**:
+```
+CRITICAL OUTPUT PROTOCOL: Your FIRST action must be calling Write tool with the full research.md content. Do NOT explain, narrate, or preview. After Write succeeds, output EXACTLY 3 lines:
+✓ research.md generated
+Recommendations: N
+Next: /curdx-flow:spec --phase=requirements
+
+FORBIDDEN: explanations, summaries, findings lists. The file is the deliverable.
+---
+```
+
 ### requirements → `flow-product-designer`
 Inputs: `research.md`.
 Output: `requirements.md` with user stories (US-NN), acceptance criteria (AC-N.N), functional requirements (FR-NN), non-functional requirements (NFR-*).
 
+**Dispatch prompt prefix (MANDATORY)**:
+```
+CRITICAL OUTPUT PROTOCOL: Your FIRST action must be calling Write tool with the full requirements.md content. Do NOT explain, narrate, or preview. After Write succeeds, output EXACTLY 4 lines:
+✓ requirements.md generated
+User stories: N
+Functional requirements: N
+Next: /curdx-flow:spec --phase=design
+
+FORBIDDEN: explanations, summaries, US/AC lists. The file is the deliverable.
+---
+```
+
 ### design → `flow-architect`
 Inputs: `research.md` + `requirements.md`.
 Output: `design.md` with architecture decisions (AD-NN), component boundaries, data models, error-path design, mermaid diagrams (when they clarify). Uses `sequential-thinking` MCP proportional to the genuine tradeoff surface.
 
+**Dispatch prompt prefix (MANDATORY)**:
+```
+CRITICAL OUTPUT PROTOCOL: Your FIRST action must be calling Write tool with the full design.md content. Do NOT explain, narrate, or preview. After Write succeeds, output EXACTLY 4 lines:
+✓ design.md generated
+Architecture decisions: N
+Components: N
+Next: /curdx-flow:spec --phase=tasks
+
+FORBIDDEN: explanations, summaries, AD lists, tech stack lists, warnings. The file is the deliverable.
+---
+```
+
 ### tasks → `flow-planner`
 Inputs: all three prior files + `.flow/PROJECT.md` tech stack.
 Output: `tasks.md` — POC-First 5-phase decomposition with per-task Verify commands, multi-source coverage audit against FR/AC/AD/Research/Decisions.
 
+**Dispatch prompt prefix (MANDATORY)**:
+```
+CRITICAL OUTPUT PROTOCOL: Your FIRST action must be calling Write tool with the full tasks.md content. Do NOT explain, narrate, or preview. After Write succeeds, output EXACTLY 5 lines:
+✓ tasks.md generated
+Total tasks: N
+Coverage audit: PASS
+Phases: 1-5
+Next: /curdx-flow:implement
+
+FORBIDDEN: explanations, summaries, task lists. The file is the deliverable.
+---
+```
+
 After each phase completes successfully, update `.state.json`:
 
 ```json

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@curdx/flow",
-  "version": "2.0.4",
+  "version": "2.0.6",
   "description": "CLI installer for CurdX-Flow — AI engineering workflow meta-framework for Claude Code",
   "type": "module",
   "bin": {