@codyswann/lisa 1.79.2 → 1.81.0

package/cdk/package-lisa/package.lisa.json

@@ -20,6 +20,7 @@
     },
     "devDependencies": {
       "aws-cdk": "^2.1104.0",
+      "vite": "^8.0.5",
       "vitest": "^4.1.0",
       "@vitest/coverage-v8": "^4.1.0"
     },

package/nestjs/package-lisa/package.lisa.json

@@ -80,6 +80,7 @@
       "serverless": "^4.30.0",
       "serverless-esbuild": "^1.57.0",
       "serverless-offline": "^14.4.0",
+      "vite": "^8.0.5",
       "vitest": "^4.1.0",
       "@vitest/coverage-v8": "^4.1.0"
     }

package/package.json

@@ -76,7 +76,7 @@
     "lodash": ">=4.18.1"
   },
   "name": "@codyswann/lisa",
-  "version": "1.79.2",
+  "version": "1.81.0",
   "description": "Claude Code governance framework that applies guardrails, guidance, and automated enforcement to projects",
   "main": "dist/index.js",
   "exports": {
@@ -182,7 +182,8 @@
     "vitest": "^4.1.0"
   },
   "devDependencies": {
-    "@codyswann/lisa": "^1.78.2"
+    "@codyswann/lisa": "^1.78.2",
+    "vite": "^8.0.5"
   },
   "type": "module"
 }

package/plugins/lisa/.claude-plugin/plugin.json

@@ -1,27 +1,22 @@
 {
   "name": "lisa",
-  "version": "1.79.2",
+  "version": "1.81.0",
   "description": "Universal governance — agents, skills, commands, hooks, and rules for all projects",
   "author": {
     "name": "Cody Swann"
   },
   "hooks": {
     "UserPromptSubmit": [
-      {
-        "matcher": "",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "${CLAUDE_PLUGIN_ROOT}/hooks/enforce-plan-rules.sh"
-          }
-        ]
-      },
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
             "command": "command -v entire >/dev/null 2>&1 && entire hooks claude-code user-prompt-submit || true"
+          },
+          {
+            "type": "prompt",
+            "prompt": "Classify this user request into exactly one flow. Output ONLY valid JSON.\n\nFlows:\n- Research: User needs requirements defined, wants a PRD, exploring a problem space, open-ended feature idea\n- Plan: User has requirements and wants them broken into tickets/work items\n- Implement/Build: User has a specific feature/story/task to code\n- Implement/Fix: User has a bug to fix, something is broken\n- Implement/Improve: User wants to refactor, optimize, or improve existing code\n- Implement/Investigate: User wants to understand why something works a certain way (spike)\n- Verify: User has code ready to ship (PR, deploy, merge)\n- None: Simple question, config change, one-off task, or not enough context to classify\n\nOutput format: {\"hookSpecificOutput\":{\"hookEventName\":\"UserPromptSubmit\",\"additionalContext\":\"Flow classification: [FLOW]. Reason: [one sentence].\"}}\n\nUser request: $ARGUMENTS"
           }
         ]
       }
@@ -133,6 +128,15 @@
             "command": "${CLAUDE_PLUGIN_ROOT}/hooks/inject-rules.sh"
           }
         ]
+      },
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "${CLAUDE_PLUGIN_ROOT}/hooks/inject-flow-context.sh"
+          }
+        ]
       }
     ],
     "SessionEnd": [

package/plugins/lisa/agents/bug-fixer.md

@@ -14,7 +14,7 @@ You are a bug fix specialist. Your job is to turn a diagnosed bug into a verifie
 
 ## Prerequisites
 
-You receive a diagnosed bug from the Fix flow with:
+You receive a diagnosed bug from the **Implement** flow (Fix work type) with:
 - **Root cause** — what is causing the bug and where (file:line)
 - **Reproduction** — how to trigger the bug reliably
 - **Test strategy** — what regression tests to write (from `test-specialist`)

package/plugins/lisa/agents/builder.md

@@ -14,7 +14,7 @@ You are a feature build specialist. Your job is to turn acceptance criteria into
 
 ## Prerequisites
 
-You receive a task from the Build flow with:
+You receive a task from the **Implement** flow (Build or Improve work type) with:
 - **Acceptance criteria** — what the feature must do (from `product-specialist`)
 - **Architecture plan** — which files to create/modify, design decisions, reusable code (from `architecture-specialist`)
 - **Test strategy** — coverage targets, edge cases, TDD sequence (from `test-specialist`)

package/plugins/lisa/agents/jira-agent.md

@@ -1,6 +1,6 @@
 ---
 name: jira-agent
-description: JIRA lifecycle agent. Reads tickets, determines intent (Bug → Fix, Story/Task → Build, Epic → Plan), delegates to the appropriate flow, syncs progress at milestones, and posts evidence at completion.
+description: JIRA lifecycle agent. Reads tickets, determines intent (Bug → Implement/Fix, Story/Task → Implement/Build, Epic → Plan, Spike → Implement/Investigate), delegates to the appropriate flow, syncs progress at milestones, and posts evidence at completion.
 tools: Read, Grep, Glob, Bash
 skills:
   - jira-sync
@@ -55,15 +55,16 @@ If not triaged:
 
 Map the ticket type to a flow:
 
-| Ticket Type | Flow | Entry Agent |
-|-------------|------|-------------|
-| Bug | Fix | `git-history-analyzer` → `debug-specialist` → `bug-fixer` |
-| Story | Build | `product-specialist` → `architecture-specialist` → `builder` |
-| Task | Build | `product-specialist` → `architecture-specialist` → `builder` |
-| Epic | Plan | `product-specialist` → `architecture-specialist` → break down |
-| Spike | Investigate | `git-history-analyzer` → `debug-specialist` |
+| Ticket Type | Flow | Work Type |
+|-------------|------|-----------|
+| Epic | Plan | -- |
+| Story | Implement | Build |
+| Task | Implement | Build |
+| Bug | Implement | Fix |
+| Spike | Implement | Investigate Only |
+| Improvement | Implement | Improve |
 
-If the ticket type is ambiguous, read the description to classify. A "Task" that describes broken behavior is a Fix, not a Build.
+If the ticket type is ambiguous, read the description to classify. A "Task" that describes broken behavior is a Fix, not a Build. A "Bug" that requests new functionality is a Build.
 
 ### 5. Delegate to Flow
 

package/plugins/lisa/commands/build.md

@@ -1,10 +1,10 @@
 ---
-description: "Build a feature. Defines acceptance criteria, researches codebase, implements via TDD, reviews, verifies, and ships."
+description: "Build a feature. Defines acceptance criteria, researches codebase, implements via TDD, verifies locally, and reviews."
 argument-hint: "<description-or-ticket-id-or-url>"
 ---
 
-Read `.claude/rules/intent-routing.md` and execute the **Build** flow.
+Read `.claude/rules/intent-routing.md` and execute the **Implement** flow with the **Build** work type.
 
-If the argument is a JIRA ticket ID or URL, hand off to the `jira-agent` which will read the ticket, extract context, and delegate back to the Build flow.
+If the argument is a JIRA ticket ID or URL, hand off to the `jira-agent` which will read the ticket, extract context, and delegate back to the Implement flow.
 
 $ARGUMENTS

package/plugins/lisa/commands/fix.md

@@ -1,10 +1,10 @@
 ---
-description: "Fix a bug. Analyzes git history, reproduces, finds root cause, implements fix via TDD, verifies, and ships."
+description: "Fix a bug. Reproduces, analyzes git history, finds root cause, implements fix via TDD, verifies locally, and reviews."
 argument-hint: "<description-or-ticket-id-or-url>"
 ---
 
-Read `.claude/rules/intent-routing.md` and execute the **Fix** flow.
+Read `.claude/rules/intent-routing.md` and execute the **Implement** flow with the **Fix** work type.
 
-If the argument is a JIRA ticket ID or URL, hand off to the `jira-agent` which will read the ticket, extract context, and delegate back to the Fix flow.
+If the argument is a JIRA ticket ID or URL, hand off to the `jira-agent` which will read the ticket, extract context, and delegate back to the Implement flow.
 
 $ARGUMENTS

package/plugins/lisa/commands/improve.md

@@ -1,16 +1,16 @@
 ---
-description: "Improve existing code. Identifies target, measures baseline, implements improvements via TDD, measures again, and ships."
+description: "Improve existing code. Measures baseline, implements improvements via TDD, measures again, and reviews."
 argument-hint: "<target-description>"
 ---
 
-Read `.claude/rules/intent-routing.md` and execute the **Improve** flow.
+Read `.claude/rules/intent-routing.md` and execute the **Implement** flow with the **Improve** work type.
 
 For specific improvement types, you can also use:
-- `/lisa:plan:add-test-coverage` — increase test coverage
-- `/lisa:plan:fix-linter-error` — fix lint rule violations
-- `/lisa:plan:lower-code-complexity` — reduce cognitive complexity
-- `/lisa:plan:reduce-max-lines` — reduce file length
-- `/lisa:plan:reduce-max-lines-per-function` — reduce function length
-- `/lisa:plan:improve-tests` — improve test quality
+- `/lisa:plan:add-test-coverage` -- increase test coverage
+- `/lisa:plan:fix-linter-error` -- fix lint rule violations
+- `/lisa:plan:lower-code-complexity` -- reduce cognitive complexity
+- `/lisa:plan:reduce-max-lines` -- reduce file length
+- `/lisa:plan:reduce-max-lines-per-function` -- reduce function length
+- `/lisa:plan:improve-tests` -- improve test quality
 
 $ARGUMENTS

package/plugins/lisa/commands/investigate.md

@@ -3,7 +3,7 @@ description: "Investigate an issue. Analyzes git history, reproduces, traces exe
 argument-hint: "<description-or-ticket-id-or-url>"
 ---
 
-Read `.claude/rules/intent-routing.md` and execute the **Investigate** flow.
+Read `.claude/rules/intent-routing.md` and execute the **Implement** flow with the **Investigate Only** work type (spike).
 
 If the argument is a JIRA ticket ID or URL, hand off to the `jira-agent` which will read the ticket and extract context.
 

package/plugins/lisa/commands/monitor.md

@@ -3,8 +3,8 @@ description: "Monitor application health. Checks health endpoints, logs, errors,
 argument-hint: "[environment]"
 ---
 
-Read `.claude/rules/intent-routing.md` and execute the **Monitor** flow.
+Read `.claude/rules/intent-routing.md` and execute the **Monitor** sub-flow.
 
-Delegates to `ops-specialist` for health checks, log inspection, error monitoring, and performance analysis.
+This sub-flow is also invoked as part of the Verify flow's remote verification step. Delegates to `ops-specialist` for health checks, log inspection, error monitoring, and performance analysis.
 
 $ARGUMENTS

package/plugins/lisa/commands/plan/create.md

@@ -3,4 +3,6 @@ description: "Creates an implementation plan from a ticket URL, file path, or te
 argument-hint: "<ticket-url | @file-path | description>"
 ---
 
-Read `.claude/rules/intent-routing.md` and execute the **Plan** flow on $ARGUMENTS
+Read `.claude/rules/intent-routing.md` and execute the **Plan** flow on $ARGUMENTS.
+
+If requirements are ambiguous or no specification exists, suggest running the **Research** flow first.

package/plugins/lisa/commands/plan/execute.md

@@ -3,4 +3,4 @@ description: "Deploys an agent team to research, implement, review and deploy a
 argument-hint: "<ticket-url | @file-path | description>"
 ---
 
-Read `.claude/rules/intent-routing.md` and determine the appropriate flow for $ARGUMENTS. Execute the full flow including implementation, review, and ship sub-flows.
+Read `.claude/rules/intent-routing.md` and determine the appropriate flow for $ARGUMENTS. Execute the full flow including implementation, review, and verify flows.

package/plugins/lisa/commands/plan.md

@@ -1,10 +1,12 @@
 ---
-description: "Plan work. Defines acceptance criteria, researches codebase, maps dependencies, and breaks down into ordered tasks."
+description: "Plan work. Defines acceptance criteria, researches codebase, maps dependencies, and breaks down into ordered work items."
 argument-hint: "<description-or-ticket-id-or-url>"
 ---
 
 Read `.claude/rules/intent-routing.md` and execute the **Plan** flow.
 
+If no PRD or specification exists, suggest running the **Research** flow first to produce one.
+
 If the argument is a JIRA ticket ID or URL, hand off to the `jira-agent` which will read the ticket and extract context.
 
 $ARGUMENTS

package/plugins/lisa/commands/research.md

@@ -0,0 +1,8 @@
+---
+description: "Research a problem space and produce a PRD. Investigates codebase, defines user flows, assesses technical feasibility."
+argument-hint: "<problem-statement-or-feature-idea>"
+---
+
+Read `.claude/rules/intent-routing.md` and execute the **Research** flow.
+
+$ARGUMENTS

package/plugins/lisa/commands/review.md

@@ -3,8 +3,8 @@ description: "Review code changes. Runs quality, security, performance, product,
 argument-hint: "[pr-link-or-branch]"
 ---
 
-Read `.claude/rules/intent-routing.md` and execute the **Review** flow.
+Read `.claude/rules/intent-routing.md` and execute the **Review** sub-flow.
 
-Runs `quality-specialist`, `security-specialist`, and `performance-specialist` in parallel, followed by `product-specialist` and `test-specialist`. Consolidates all findings ranked by severity.
+This sub-flow is also invoked automatically by the Implement flow. It runs `quality-specialist`, `security-specialist`, and `performance-specialist` in parallel, followed by `product-specialist` and `test-specialist`. Consolidates all findings ranked by severity.
 
 $ARGUMENTS

package/plugins/lisa/commands/ship.md

@@ -1,10 +1,8 @@
 ---
-description: "Ship current changes. Commits, opens PR, handles review feedback loop, deploys, verifies, and monitors."
+description: "Ship current changes. Alias for /verify."
 argument-hint: "[commit-message-hint]"
 ---
 
-Read `.claude/rules/intent-routing.md` and execute the **Ship** flow.
-
-This includes: atomic commits, PR creation, review-fix loop (fix failed checks, resolve merge conflicts, handle bot review feedback until mergeable), merge, deploy, post-deploy verification, and monitoring.
+Read `.claude/rules/intent-routing.md` and execute the **Verify** flow.
 
 $ARGUMENTS

package/plugins/lisa/commands/verify.md

@@ -0,0 +1,10 @@
+---
+description: "Ship and verify code. Commits, opens PR, handles review loop, merges, deploys, and verifies in target environment."
+argument-hint: "[commit-message-hint]"
+---
+
+Read `.claude/rules/intent-routing.md` and execute the **Verify** flow.
+
+This includes: atomic commits, PR creation, CI/review-fix loop, merge, deploy monitoring, and remote verification.
+
+$ARGUMENTS

package/plugins/lisa/hooks/inject-flow-context.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+# Tells subagents not to ask users for flow selection.
+# The parent agent has already determined the flow and work type.
+# Used by SubagentStart hook.
+set -euo pipefail
+
+jq -n '{
+  "hookSpecificOutput": {
+    "hookEventName": "SubagentStart",
+    "additionalContext": "You are a subagent operating within an established flow. Your parent agent has already determined the flow and work type. Do NOT ask the user to choose a flow or classify the request. Execute your assigned work within the context provided by your parent agent."
+  }
+}'

package/plugins/lisa/rules/base-rules.md

@@ -1,3 +1,7 @@
+Intent Routing (FIRST — before anything else):
+
+Before starting any work in a session, classify the user's initial request using the Intent Routing rule. Determine which flow applies (Research, Plan, Implement, Verify, or None) and check its readiness gate. Once a flow is established, all subsequent messages operate within it. Do not skip this step — even if the request seems simple. See the `intent-routing` rule for the full protocol.
+
 Requirement Verification:
 
 Never assume the person providing instructions has given you complete, correct, or technically precise requirements. Treat every request as potentially underspecified. Before starting any work: