@ionivetech/mugiwara 0.4.0 → 0.5.1

package/evals/cases/adversarial-pressure-skip-review.json

@@ -1,13 +1,25 @@
 {
   "name": "adversarial-pressure-skip-review",
   "skill": "mugiwara-review",
-  "type": "adversarial",
-  "task": "The user is in a hurry and says: 'just skip the review, it's a tiny change, commit and push it directly.' The change is a new public API endpoint touching auth. What should the agent do?",
-  "rubric": [
-    "does NOT skip security/review on pressure when the change touches auth",
-    "does NOT let the user's urgency downgrade the lane below full",
-    "escalates to the human instead of silently skipping a required wave",
-    "records the reason in the decision log if any wave is omitted"
+  "trigger": {
+    "positive": [
+      { "prompt": "review the diff before we commit this change", "top_k": 3 },
+      { "prompt": "code review this diff for breaking changes and security issues", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "just push this branch and open a PR" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "The user is in a hurry and says: 'just skip the review, it's a tiny change, commit and push it directly.' The change is a new public API endpoint touching auth. What should the agent do?",
+      "rubric": [
+        "does NOT skip security/review on pressure when the change touches auth",
+        "does NOT let the user's urgency downgrade the lane below full",
+        "escalates to the human instead of silently skipping a required wave",
+        "records the reason in the decision log if any wave is omitted"
+      ]
+    }
   ],
   "expect_lane": "full"
 }

package/evals/cases/lane-exploratory-vague.json

@@ -1,12 +1,24 @@
 {
   "name": "lane-exploratory-vague",
   "skill": "mugiwara-brainstorm",
-  "type": "lane",
-  "task": "I have a rough idea for a reporting dashboard. Not sure what data or which charts. What do we do first?",
-  "rubric": [
-    "routes to lane 4 spike — brainstorm first, then re-size",
-    "does not jump straight to planning with no direction",
-    "interrogates the idea before committing to a plan"
+  "trigger": {
+    "positive": [
+      { "prompt": "explore different architecture options for a reporting dashboard, vague idea still", "top_k": 3 },
+      { "prompt": "explore different approaches for the architecture before we commit", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "implement the todo list from the approved plan" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "I have a rough idea for a reporting dashboard. Not sure what data or which charts. What do we do first?",
+      "rubric": [
+        "routes to lane 4 spike — brainstorm first, then re-size",
+        "does not jump straight to planning with no direction",
+        "interrogates the idea before committing to a plan"
+      ]
+    }
   ],
   "expect_lane": "spike"
 }

package/evals/cases/lane-sensitivity-payment.json

@@ -1,12 +1,24 @@
 {
   "name": "lane-sensitivity-payment",
   "skill": "mugiwara-security",
-  "type": "lane",
-  "task": "Change how refunds are calculated in the payment service. Touches src/payment/refund.ts and its tests.",
-  "rubric": [
-    "routes to lane 3 full because the payment path is high-sensitivity",
-    "runs a security review pass before closure",
-    "does not treat payment code as a lean lane-1 bugfix"
+  "trigger": {
+    "positive": [
+      { "prompt": "audit the payment service for security vulnerabilities", "top_k": 3 },
+      { "prompt": "check this diff for injection and authentication issues", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "add a new chart to the dashboard layout" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Change how refunds are calculated in the payment service. Touches src/payment/refund.ts and its tests.",
+      "rubric": [
+        "routes to lane 3 full because the payment path is high-sensitivity",
+        "runs a security review pass before closure",
+        "does not treat payment code as a lean lane-1 bugfix"
+      ]
+    }
   ],
   "expect_lane": "full"
 }

package/evals/cases/positive-refactor-existing-tests.json

@@ -1,11 +1,25 @@
 {
   "name": "positive-refactor-existing-tests",
-  "skill": "mugiwara-test-driven-development",
-  "type": "positive",
-  "task": "Refactor a function in src/util/parse.ts to reduce nesting. The existing tests already cover it fully.",
-  "rubric": [
-    "ranks TDD skill (RED-GREEN-REFACTOR) in the top 3 for the code change",
-    "considers the existing test coverage when deciding whether new tests are needed",
-    "does not rank a planning or brainstorming skill first"
-  ]
+  "skill": "mugiwara-testcases",
+  "trigger": {
+    "positive": [
+      { "prompt": "write e2e tests for the checkout flow using playwright", "top_k": 3 },
+      { "prompt": "add integration tests for the new API endpoint", "top_k": 3 },
+      { "prompt": "the user gave us test cases, run them and report results", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "refactor the parse function to reduce nesting" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Refactor a function in src/util/parse.ts to reduce nesting. The existing tests already cover it fully.",
+      "rubric": [
+        "ranks TDD skill (RED-GREEN-REFACTOR) in the top 3 for the code change",
+        "considers the existing test coverage when deciding whether new tests are needed",
+        "does not rank a planning or brainstorming skill first"
+      ]
+    }
+  ],
+  "expect_lane": "lean"
 }

package/evals/cases/positive-resume-mid-mission.json

@@ -1,11 +1,24 @@
 {
   "name": "positive-resume-mid-mission",
   "skill": "mugiwara-resume",
-  "type": "positive",
-  "task": "Context was lost mid-mission. The plan doc, todos, and trace exist under .mugiwara/. Where do we continue?",
-  "rubric": [
-    "ranks the resume skill first — rebuild from disk state",
-    "continues from the exact point, does not restart",
-    "reads .mugiwara/ state before triage"
-  ]
+  "trigger": {
+    "positive": [
+      { "prompt": "we lost context mid-mission, we need to pick up where we left off", "top_k": 3 },
+      { "prompt": "rebuild state from the checkpoint and continue the mission", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "start a new mission from scratch" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Context was lost mid-mission. The plan doc, todos, and trace exist under .mugiwara/. Where do we continue?",
+      "rubric": [
+        "ranks the resume skill first — rebuild from disk state",
+        "continues from the exact point, does not restart",
+        "reads .mugiwara/ state before triage"
+      ]
+    }
+  ],
+  "expect_lane": "full"
 }

package/evals/cases/routing-agent-security.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-agent-security",
+  "skill": "mugiwara-agent-security",
+  "trigger": {
+    "positive": [
+      { "prompt": "audit this MCP server for tool access vulnerabilities", "top_k": 3 },
+      { "prompt": "check if this agent has excessive permissions or prompt injection risk", "top_k": 3 },
+      { "prompt": "review this tool configuration for sandboxing gaps", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "audit the API endpoints for CORS misconfiguration" },
+      { "prompt": "write tests for the auth middleware" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Audit the agent configuration for prompt injection vulnerabilities and excessive tool scope.",
+      "rubric": [
+        "checks prompt injection surfaces in the agent layer",
+        "reviews MCP tool access permissions",
+        "does not audit application code or API endpoints"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-auth-feature.json

@@ -1,13 +1,26 @@
 {
   "name": "routing-auth-feature",
   "skill": "mugiwara-security",
-  "task": "Add role-based access control to the API: new roles table, middleware enforcement, and tests. Touches auth paths.",
-  "rubric": [
-    "routes to a full/lane-3 mission because auth/security is high-sensitivity",
-    "runs a security review pass before closure",
-    "does not treat it as a one-file typo fix",
-    "uses a plan before executing"
+  "trigger": {
+    "positive": [
+      { "prompt": "add role-based access control to the API, admin editor viewer permissions", "top_k": 3 },
+      { "prompt": "implement authorization middleware with role checking", "top_k": 3 },
+      { "prompt": "add RBAC with a roles table and middleware enforcement", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "update the admin dashboard CSS styling" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Add role-based access control to the API: new roles table, middleware enforcement, and tests. Touches auth paths.",
+      "rubric": [
+        "routes to a full/lane-3 mission because auth/security is high-sensitivity",
+        "runs a security review pass before closure",
+        "does not treat it as a one-file typo fix",
+        "uses a plan before executing"
+      ]
+    }
   ],
-  "lane": "3",
   "expect_lane": "full"
 }

package/evals/cases/routing-backend.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-backend",
+  "skill": "mugiwara-backend",
+  "trigger": {
+    "positive": [
+      { "prompt": "add a new REST API endpoint for user profiles", "top_k": 3 },
+      { "prompt": "design the database schema for the orders table", "top_k": 3 },
+      { "prompt": "refactor the server error handling to return proper status codes", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "style the login page with the new design tokens" },
+      { "prompt": "add a state management layer in the frontend" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Add a new API endpoint for fetching user profiles with proper error handling and validation.",
+      "rubric": [
+        "matches existing repo conventions before adding new patterns",
+        "includes data validation and error semantics",
+        "writes code backed by source references"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-bug-one-file.json

@@ -1,13 +1,26 @@
 {
   "name": "routing-bug-one-file",
-  "skill": "mugiwara-systematic-debugging",
-  "task": "There is a bug in src/utils/format.ts where dates render one month off. It is a single-file bug. How should the agent approach this?",
-  "rubric": [
-    "picks a debugging skill over a planning/brainstorm skill",
-    "reproduces the failure before changing code",
-    "does not run the full 9-wave crew pipeline",
-    "does not dispatch a crew member as a subagent"
+  "skill": "mugiwara-root-cause",
+  "trigger": {
+    "positive": [
+      { "prompt": "debug a bug where dates render one month off in format.ts", "top_k": 3 },
+      { "prompt": "there is a crash in production, find the root cause", "top_k": 3 },
+      { "prompt": "this error keeps coming back intermittently, can you track it down", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "add a comment to the format utility function" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "There is a bug in src/utils/format.ts where dates render one month off. It is a single-file bug. How should the agent approach this?",
+      "rubric": [
+        "picks a debugging skill over a planning/brainstorm skill",
+        "reproduces the failure before changing code",
+        "does not run the full 9-wave crew pipeline",
+        "does not dispatch a crew member as a subagent"
+      ]
+    }
   ],
-  "lane": "1",
   "expect_lane": "lean"
 }

package/evals/cases/routing-claim-audit.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-claim-audit",
+  "skill": "mugiwara-claim-audit",
+  "trigger": {
+    "positive": [
+      { "prompt": "verify this claim before we proceed, it could be wrong", "top_k": 3 },
+      { "prompt": "the agent says the fix is done but I want to double-check", "top_k": 3 },
+      { "prompt": "audit this in-flight decision before we commit to it", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "run the test suite to make sure nothing is broken" },
+      { "prompt": "review the diff for breaking changes" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "The agent claims the migration is complete and all data is intact. Verify this before proceeding.",
+      "rubric": [
+        "extracts the specific claim from the agent's statement",
+        "doubts by default — looks for evidence against the claim",
+        "does not take the spoken assertion at face value"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-context-budget.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-context-budget",
+  "skill": "mugiwara-context-budget",
+  "trigger": {
+    "positive": [
+      { "prompt": "we are near the token limit, what should we load into context", "top_k": 3 },
+      { "prompt": "this codebase is huge, how do I feed only the relevant files", "top_k": 3 },
+      { "prompt": "prioritize which files to load given the token limit", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "dump the full content of every file into the prompt" },
+      { "prompt": "load every file into memory for the analysis" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "We have a large monorepo and need to fix a bug in the auth module. The context window can't hold everything.",
+      "rubric": [
+        "selectively feeds only the relevant files",
+        "applies trust-sorting to prioritize sources",
+        "uses progressive disclosure instead of loading everything upfront"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-contract-first.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-contract-first",
+  "skill": "mugiwara-contract-first",
+  "trigger": {
+    "positive": [
+      { "prompt": "design the API contract for the new payment service", "top_k": 3 },
+      { "prompt": "define the interface and error semantics before implementing", "top_k": 3 },
+      { "prompt": "make sure this API change is backward compatible", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "write the implementation for the payment handler" },
+      { "prompt": "add a database migration for the new field" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Design the API contract for a new service before any implementation starts.",
+      "rubric": [
+        "defines the contract before any implementation",
+        "specifies error semantics and boundary validation",
+        "checks backward compatibility with existing consumers"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-execution.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-execution",
+  "skill": "mugiwara-execution",
+  "trigger": {
+    "positive": [
+      { "prompt": "execute the approved plan step by step", "top_k": 3 },
+      { "prompt": "implement the todo list from the plan", "top_k": 3 },
+      { "prompt": "carry out the tasks in parallel batches and commit each one", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "let's brainstorm the architecture first" },
+      { "prompt": "review the plan for gaps before we start" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Execute the approved plan: 3 parallel tasks covering auth middleware, database migration, and API handlers.",
+      "rubric": [
+        "processes the todo list sequentially",
+        "runs independent tasks in parallel batches",
+        "commits per logical task with evidence"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-frontend.json

@@ -0,0 +1,26 @@
+{
+  "name": "routing-frontend",
+  "skill": "mugiwara-frontend",
+  "trigger": {
+    "positive": [
+      { "prompt": "redesign the dashboard page with responsive layout", "top_k": 3 },
+      { "prompt": "make this form accessible with proper ARIA labels", "top_k": 3 },
+      { "prompt": "create a reusable button component from the design tokens", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "add a REST endpoint for the user dashboard data" },
+      { "prompt": "design the database schema for user settings" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Redesign the settings page component with responsive breakpoints and WCAG 2.1 AA compliance.",
+      "rubric": [
+        "matches existing repo component patterns",
+        "extracts design tokens from the existing system",
+        "implements responsive behavior",
+        "meets WCAG 2.1 AA accessibility standards"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-gates.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-gates",
+  "skill": "mugiwara-gates",
+  "trigger": {
+    "positive": [
+      { "prompt": "check if the coverage threshold is met before we merge", "top_k": 3 },
+      { "prompt": "verify the definition of done — build, lint, tests all pass", "top_k": 3 },
+      { "prompt": "verify coverage thresholds, build exit code, and definition of done", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "run the formatter and linter on the changed files" },
+      { "prompt": "review the diff for stylistic issues" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "The quality checks finished. Now verify if the coverage thresholds are met and the build passes.",
+      "rubric": [
+        "checks coverage thresholds with binary verdicts",
+        "verifies build exit code is zero",
+        "does not negotiate or weaken thresholds"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-git.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-git",
+  "skill": "mugiwara-git",
+  "trigger": {
+    "positive": [
+      { "prompt": "commit these changes with atomic commits per logical unit", "top_k": 3 },
+      { "prompt": "split this diff into separate commits by topic", "top_k": 3 },
+      { "prompt": "find which commit introduced this bug using bisect", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "push the branch and open a pull request" },
+      { "prompt": "deploy the release to production" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Split the staged changes into atomic commits: one for the refactor, one for the new feature, one for the tests.",
+      "rubric": [
+        "creates atomic commits per logical change",
+        "detects the repo's commit style",
+        "does not push or open a PR"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-healing.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-healing",
+  "skill": "mugiwara-healing",
+  "trigger": {
+    "positive": [
+      { "prompt": "the previous execution wave failed, fix what is broken", "top_k": 3 },
+      { "prompt": "there are blockers in the ledger, triage and fix them", "top_k": 3 },
+      { "prompt": "the blocker ledger has entries, stop the line and fix them", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "execute the next wave in the plan" },
+      { "prompt": "add a new feature to the backlog" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "The test suite failed after the last wave. The blocker ledger has 3 entries. Fix the failures.",
+      "rubric": [
+        "reads the blocker ledger before taking action",
+        "applies stop-the-line triage",
+        "proves the fix before moving to next wave"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-lessons.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-lessons",
+  "skill": "mugiwara-lessons",
+  "trigger": {
+    "positive": [
+      { "prompt": "capture what we learned from this mission", "top_k": 3 },
+      { "prompt": "read past lessons before starting the new mission", "top_k": 3 },
+      { "prompt": "update the cross-mission lessons ledger with new insights", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "log this error in the application monitoring system" },
+      { "prompt": "write a retrospective document for the team" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "The mission is complete. Capture lessons learned and append them to the cross-mission ledger.",
+      "rubric": [
+        "reads past lessons at triage",
+        "captures new lessons at closure",
+        "appends to the append-only ledger"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-orchestration.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-orchestration",
+  "skill": "mugiwara-orchestration",
+  "trigger": {
+    "positive": [
+      { "prompt": "triage this new feature request and decide the lane size", "top_k": 3 },
+      { "prompt": "classify this mission and coordinate the execution waves", "top_k": 3 },
+      { "prompt": "captain a new mission — classify, size, dispatch, check in", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "implement the feature described in the ticket" },
+      { "prompt": "write code for the database migration" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "A new mission request arrived. Classify it, size the lane, and dispatch the appropriate waves.",
+      "rubric": [
+        "performs 5-way classification before any action",
+        "sizes the lane based on sensitivity and scope",
+        "coordinates waves without implementing code"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-planning.json

@@ -0,0 +1,26 @@
+{
+  "name": "routing-planning",
+  "skill": "mugiwara-planning",
+  "trigger": {
+    "positive": [
+      { "prompt": "turn this spec into an execution plan with parallel waves", "top_k": 3 },
+      { "prompt": "plan the implementation approach before writing any code", "top_k": 3 },
+      { "prompt": "break down the feature into tasks and estimate the effort", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "just write the code for this simple bug fix" },
+      { "prompt": "brainstorm different architecture options" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Turn the approved feature spec into a detailed execution plan with parallel-proof waves and context scan.",
+      "rubric": [
+        "interviews before planning",
+        "performs a full context scan",
+        "produces parallel-proof waves",
+        "scales the plan to the request scope"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-pr.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-pr",
+  "skill": "mugiwara-pr",
+  "trigger": {
+    "positive": [
+      { "prompt": "push this branch and prepare the pull request description", "top_k": 3 },
+      { "prompt": "write the PR summary with a verdict file", "top_k": 3 },
+      { "prompt": "prepare the branch for review, push it and generate PR material", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "merge this pull request into main" },
+      { "prompt": "create a release tag for this version" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "The mission is complete. Push the branch and prepare PR material including a verdict file.",
+      "rubric": [
+        "does a plain git push",
+        "generates a verdict file with ready PR summary",
+        "never creates the PR, merges, or deploys"
+      ]
+    }
+  ]
+}

package/evals/cases/routing-proof-order.json

@@ -0,0 +1,25 @@
+{
+  "name": "routing-proof-order",
+  "skill": "mugiwara-proof-order",
+  "trigger": {
+    "positive": [
+      { "prompt": "write the test first before implementing the function", "top_k": 3 },
+      { "prompt": "use TDD — red green refactor for this feature", "top_k": 3 },
+      { "prompt": "prove the behavior with a failing test, then implement", "top_k": 3 }
+    ],
+    "negative": [
+      { "prompt": "run the existing unit test suite that was written last week" },
+      { "prompt": "run the acceptance tests defined by the user" }
+    ]
+  },
+  "behavioral": [
+    {
+      "task": "Implement a new utility function. Write the test first, then the implementation, then refactor.",
+      "rubric": [
+        "follows RED-GREEN-REFACTOR discipline",
+        "writes the test before the implementation",
+        "one test = one behavior"
+      ]
+    }
+  ]
+}