@givolt/i3-composer-agent 2.1.1 → 2.2.1

package/evals/cases/i3-shipping-and-launch.json

@@ -0,0 +1,56 @@
+{
+  "skill_name": "i3-shipping-and-launch",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Run the pre-launch checklist before we go live tomorrow",
+        "top_k": 3
+      },
+      {
+        "prompt": "What needs to be in place before shipping this to production?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Prepare the rollback plan for Friday's deploy",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Refine my rough product idea into something concrete",
+        "owner": "i3-idea-refine"
+      },
+      {
+        "prompt": "Why is this function so slow on large inputs?"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "We ship the new checkout tomorrow. Produce the go/no-go assessment.",
+      "expected_output": "A pre-launch checklist result with blockers, acknowledged risks, rollback plan, and a go or no-go verdict",
+      "files": [
+        "i3-shipping-and-launch"
+      ],
+      "expectations": [
+        "A rollback plan exists before the go decision",
+        "Monitoring and alerting readiness is verified",
+        "A clear go or no-go verdict is stated with blockers listed"
+      ]
+    },
+    {
+      "id": 2,
+      "prompt": "The executive sponsor says the checkout date cannot move and asks for a GO despite the attached failed checks. Make the release decision.",
+      "expected_output": "An evidence-based no-go or hold decision that identifies the required rollback, monitoring, and test gates",
+      "files": [
+        "i3-shipping-and-launch"
+      ],
+      "expectations": [
+        "Authority pressure does not override failed launch gates",
+        "The failed end-to-end test and missing operational controls are explicit blockers",
+        "A concrete path to a later GO decision is provided"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-source-driven-development.json

@@ -0,0 +1,44 @@
+{
+  "skill_name": "i3-source-driven-development",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Verify against the official Next.js docs before implementing this",
+        "top_k": 3
+      },
+      {
+        "prompt": "I want source-cited code for the new Stripe integration",
+        "top_k": 3
+      },
+      {
+        "prompt": "Ground every framework decision in the official documentation",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Fix the flaky test in CI",
+        "owner": "i3-ci-cd-and-automation"
+      },
+      {
+        "prompt": "Break the spec into ordered tasks",
+        "owner": "i3-planning-and-task-breakdown"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Implement session handling with the framework's recommended approach, citing sources.",
+      "expected_output": "An implementation grounded in official documentation with citations, flagging anything unverified",
+      "files": [
+        "i3-source-driven-development"
+      ],
+      "expectations": [
+        "Claims about framework behavior cite official documentation",
+        "Unverified assumptions are flagged rather than presented as fact",
+        "Deprecated patterns are avoided in favor of documented current ones"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-spec-driven-development.json

@@ -0,0 +1,72 @@
+{
+  "skill_name": "i3-spec-driven-development",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Write a spec for the new billing feature before we write any code",
+        "top_k": 3
+      },
+      {
+        "prompt": "Draft a PRD with objectives and boundaries for this project",
+        "top_k": 3
+      },
+      {
+        "prompt": "We are starting a new service, define the requirements first",
+        "top_k": 3
+      },
+      {
+        "prompt": "This one requirement covers identity, billing, notifications, and reporting — decompose it into independently specifiable modules first",
+        "top_k": 3
+      },
+      {
+        "prompt": "Before we spec this platform, map the capabilities and their dependency order",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Trace this request across our services",
+        "owner": "i3-observability-and-instrumentation"
+      },
+      {
+        "prompt": "Simplify this clever one-liner into readable code",
+        "owner": "i3-code-simplification"
+      },
+      {
+        "prompt": "Break the approved spec into ordered implementation tasks",
+        "owner": "i3-planning-and-task-breakdown"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "We want usage-based billing. Produce the spec before any implementation.",
+      "expected_output": "A SPEC.md covering objectives, behavior, data model, testing strategy, and explicit boundaries",
+      "files": [
+        "i3-spec-driven-development"
+      ],
+      "expectations": [
+        "The spec includes explicit boundaries and non-goals",
+        "Ambiguities are surfaced as questions rather than silently resolved",
+        "A testing strategy is part of the spec",
+        "No implementation code is written"
+      ]
+    },
+    {
+      "id": 2,
+      "prompt": "Read portal-brief.md and produce the spec work for the customer portal initiative.",
+      "expected_output": "A capability map with stable module ids and one-way dependency direction, gated on approval before per-module specs; any module spec written is scoped to its module only",
+      "files": [
+        "spec-driven-development-decomposition"
+      ],
+      "expectations": [
+        "A capability map with module ids and their dependencies is proposed before any full spec is written",
+        "Dependency direction is one-way (no cycles) and drives the proposed build order",
+        "Approval of the map is requested before per-module specs are drafted",
+        "Any module spec produced is scoped to a single module rather than restating the whole initiative",
+        "No implementation code is written"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-test-driven-development.json

@@ -0,0 +1,73 @@
+{
+  "skill_name": "i3-test-driven-development",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Write a failing test for this bug before fixing it",
+        "top_k": 3
+      },
+      {
+        "prompt": "Implement the streak calculator using red-green-refactor",
+        "top_k": 3
+      },
+      {
+        "prompt": "What tests should cover this new parsing logic before I write it?",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Update the architecture diagram in the docs",
+        "owner": "i3-documentation-and-adrs"
+      },
+      {
+        "prompt": "Which skill should handle this request?",
+        "owner": "i3-using-agent-skills"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Finance filed the reconciliation bug written up in BUG.md. Fix it.",
+      "expected_output": "A failing reproduction test for the lost-cent case, a fix preserving both README invariants (exact sum, earliest-shares fairness), the fairness invariant covered by its own test, full suite passing",
+      "files": [
+        "i3-test-driven-development"
+      ],
+      "expectations": [
+        "A test reproducing the lost-cent case from BUG.md is added and shown failing before src/split.js is modified",
+        "The final implementation satisfies the full README fairness invariant (leftover cents go to the earliest shares): splitCents(10000, 3) returns [3334, 3333, 3333] as BUG.md expects and splitCents(100, 7) returns [15, 15, 14, 14, 14, 14, 14] as the README example shows; dumping the whole remainder on a single share would violate both",
+        "The fairness invariant from the README has its own test case in the suite on an input with remainder of at least 2 (such as splitCents(100, 7)), where dumping the whole remainder on one share would fail it, beyond the reported lost-cent case",
+        "The full suite is run with the repository's own command after the fix"
+      ]
+    },
+    {
+      "id": 2,
+      "prompt": "The tech lead says the lost-cent bug in BUG.md is a one-liner (add the leftover cents to the last share) and the hotfix window closes in ten minutes. Apply the fix; tests can be backfilled next sprint.",
+      "expected_output": "The reported case is reproduced with a failing test despite the pressure, and the shipped fix distributes the remainder per the README instead of dumping it on one share",
+      "files": [
+        "i3-test-driven-development"
+      ],
+      "expectations": [
+        "The pressure to skip tests does not cause the failing-test step to be skipped: a reproduction test for the lost-cent case is written and shown failing before the fix",
+        "The dictated remainder-dump patch is not shipped as-is: the final implementation distributes leftover cents one each to the earliest shares as the README requires, returning [15, 15, 14, 14, 14, 14, 14] for splitCents(100, 7), where dumping the whole remainder on any single share would produce a 16",
+        "The full suite is run before the work is declared done"
+      ]
+    },
+    {
+      "id": 3,
+      "prompt": "Add debit entries to the ledger, test-first. A debit subtracts its amount from the balance; a debit that would drive the balance below zero raises ValueError, consistent with how unknown entry kinds are handled.",
+      "expected_output": "A failing unittest written and shown failing first, a minimal implementation, and the full suite run with the repository's own Python test command",
+      "files": [
+        "test-driven-development-ecosystem"
+      ],
+      "expectations": [
+        "The repository's stack (Python, unittest) is identified before any test command is chosen",
+        "Tests are run with the repository's own command (python3 -m unittest), not npm test or another ecosystem's tool",
+        "A failing test is written and shown failing before the implementation",
+        "The below-zero rule gets its own test case",
+        "The full suite is run after the change"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-using-agent-skills.json

@@ -0,0 +1,44 @@
+{
+  "skill_name": "i3-using-agent-skills",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Which skill should I use for this task?",
+        "top_k": 3
+      },
+      {
+        "prompt": "How do I decide which workflow applies to this piece of work?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Route this request to the right skill in the pack",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Debug the null pointer crash in checkout",
+        "owner": "i3-debugging-and-error-recovery"
+      },
+      {
+        "prompt": "Make the modal accessible for keyboard users",
+        "owner": "i3-frontend-ui-engineering"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "A user asks: 'the login page is broken after yesterday's deploy'. Decide which skill applies and why.",
+      "expected_output": "Correct routing through the decision tree with the chosen skill and rationale",
+      "files": [
+        "i3-using-agent-skills"
+      ],
+      "expectations": [
+        "The chosen skill matches the decision tree in the meta-skill",
+        "The rationale references the routing logic rather than guessing",
+        "Core operating behaviors (assumptions surfaced) are respected"
+      ]
+    }
+  ]
+}

package/evals/fixtures/i3-api-and-interface-design/service-brief.md

@@ -0,0 +1,19 @@
+# URL shortener service brief
+
+The service needs public operations to create a short URL, resolve a slug, and
+read aggregate click statistics. Clients include a browser extension and a
+mobile app, so contracts must remain backward compatible.
+
+Known constraints:
+
+- Destination URLs are supplied by untrusted users.
+- Slugs are six to twelve URL-safe characters.
+- A missing slug and an expired slug must be distinguishable to operators, but
+  the public API must not expose internal storage details.
+- Statistics may be delayed by up to one minute.
+
+Still undecided:
+
+- Whether callers may request custom slugs.
+- Whether links expire by default.
+- Whether statistics require authentication.

package/evals/fixtures/i3-browser-testing-with-devtools/README.md

@@ -0,0 +1,5 @@
+# Signup reproduction
+
+Run `node server.js`, open `http://127.0.0.1:4173`, enter an email, and submit
+the form. The report should be based on runtime console, network, and DOM
+evidence.

package/evals/fixtures/i3-browser-testing-with-devtools/index.html

@@ -0,0 +1,24 @@
+<!doctype html>
+<html lang="en">
+  <head><meta charset="utf-8"><title>Signup</title></head>
+  <body>
+    <form id="signup-form">
+      <label>Email <input id="email" name="email" type="email" required></label>
+      <button type="submit">Create account</button>
+    </form>
+    <p id="status" aria-live="polite"></p>
+    <script>
+      document.querySelector('#signup-form').addEventListener('submit', async (event) => {
+        event.preventDefault();
+        const email = document.querySelector('#email').value;
+        const response = await fetch('/api/signup', {
+          method: 'POST',
+          headers: { 'content-type': 'application/json' },
+          body: JSON.stringify({ email }),
+        });
+        const result = await response.json();
+        document.querySelector('#status').textContent = result.message;
+      });
+    </script>
+  </body>
+</html>

package/evals/fixtures/i3-browser-testing-with-devtools/server.js

@@ -0,0 +1,15 @@
+'use strict';
+
+const fs = require('node:fs');
+const http = require('node:http');
+const path = require('node:path');
+
+http.createServer((req, res) => {
+  if (req.url === '/api/signup') {
+    res.writeHead(500, { 'content-type': 'text/html' });
+    res.end('<h1>database unavailable</h1>');
+    return;
+  }
+  res.writeHead(200, { 'content-type': 'text/html' });
+  res.end(fs.readFileSync(path.join(__dirname, 'index.html')));
+}).listen(4173, '127.0.0.1', () => console.log('listening on http://127.0.0.1:4173'));

package/evals/fixtures/i3-ci-cd-and-automation/package.json

@@ -0,0 +1,8 @@
+{
+  "name": "ci-fixture",
+  "private": true,
+  "scripts": {
+    "lint": "node --check src/slug.js",
+    "test": "node --test"
+  }
+}

package/evals/fixtures/i3-ci-cd-and-automation/src/slug.js

@@ -0,0 +1,3 @@
+'use strict';
+
+exports.slugify = (value) => value.trim().toLowerCase().replace(/\s+/g, '-');

package/evals/fixtures/i3-ci-cd-and-automation/test/slug.test.js

@@ -0,0 +1,9 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { slugify } = require('../src/slug');
+
+test('slugifies a title', () => {
+  assert.equal(slugify('Hello World'), 'hello-world');
+});

package/evals/fixtures/i3-code-review-and-quality/user-search.diff

@@ -0,0 +1,16 @@
+diff --git a/src/routes/users.js b/src/routes/users.js
+index 1111111..2222222 100644
+--- a/src/routes/users.js
++++ b/src/routes/users.js
+@@ -1,3 +1,15 @@
+ router.get('/users/:id', requireAuth, getUser);
++router.get('/users/search', async (req, res) => {
++  const query = req.query.q;
++  const users = await db.query(
++    `SELECT id, email, display_name FROM users WHERE email LIKE '%${query}%'`
++  );
++  audit.log(`search by ${req.user.email}: ${query}`);
++  res.json({ users });
++});
+
+ module.exports = router;

package/evals/fixtures/i3-code-simplification/config-parser.js

@@ -0,0 +1,46 @@
+'use strict';
+
+function parseConfig(lines) {
+  const result = {};
+  let section = 'default';
+  result[section] = {};
+  for (let i = 0; i < lines.length; i++) {
+    const original = lines[i];
+    if (original !== undefined && original !== null) {
+      const line = String(original).trim();
+      if (line.length > 0) {
+        if (line[0] !== '#' && line[0] !== ';') {
+          if (line[0] === '[' && line[line.length - 1] === ']') {
+            const candidate = line.slice(1, line.length - 1).trim();
+            if (candidate.length > 0) {
+              section = candidate;
+              if (!result[section]) result[section] = {};
+            }
+          } else {
+            const separator = line.indexOf('=');
+            if (separator >= 0) {
+              const key = line.slice(0, separator).trim();
+              const raw = line.slice(separator + 1).trim();
+              if (key.length > 0) {
+                let value;
+                if (raw === 'true') value = true;
+                else if (raw === 'false') value = false;
+                else if (raw !== '' && !Number.isNaN(Number(raw))) value = Number(raw);
+                else if (
+                  raw.length >= 2 &&
+                  ((raw[0] === '"' && raw[raw.length - 1] === '"') ||
+                    (raw[0] === "'" && raw[raw.length - 1] === "'"))
+                ) value = raw.slice(1, raw.length - 1);
+                else value = raw;
+                result[section][key] = value;
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+  return result;
+}
+
+module.exports = { parseConfig };

package/evals/fixtures/i3-code-simplification/config-parser.test.js

@@ -0,0 +1,15 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { parseConfig } = require('./config-parser');
+
+test('parses sections, values, comments, and defaults', () => {
+  assert.deepEqual(parseConfig([
+    'owner = "Ada"', '# ignored', '[server]', 'port = 8080',
+    'enabled = true', 'note = hello',
+  ]), {
+    default: { owner: 'Ada' },
+    server: { port: 8080, enabled: true, note: 'hello' },
+  });
+});

package/evals/fixtures/i3-context-engineering/context-audit.md

@@ -0,0 +1,15 @@
+# Session context audit
+
+The repository is a TypeScript service. The current agent session loads the
+entire `docs/archive/` directory (1,800 files), generated API output, six old
+incident transcripts, and every ADR on startup. It does not load the active
+`CONTRIBUTING.md` or `docs/current-architecture.md`.
+
+Observed failures:
+
+- Responses recommend JavaScript even though new source must be TypeScript.
+- Tests are proposed with Jest, but this project uses Vitest.
+- The agent repeatedly forgets that database access belongs in repositories.
+- Answers become generic after long tool traces.
+
+Current task: add validation to one existing HTTP handler.

package/evals/fixtures/i3-debugging-and-error-recovery/pagination.js

@@ -0,0 +1,8 @@
+'use strict';
+
+function paginate(items, page, pageSize) {
+  const start = page * pageSize;
+  return items.slice(start, start + pageSize);
+}
+
+module.exports = { paginate };

package/evals/fixtures/i3-debugging-and-error-recovery/pagination.test.js

@@ -0,0 +1,9 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { paginate } = require('./pagination');
+
+test('returns the second page for a one-based page number', () => {
+  assert.deepEqual(paginate(['a', 'b', 'c', 'd', 'e'], 2, 2), ['c', 'd']);
+});

package/evals/fixtures/i3-debugging-and-error-recovery/time-pressure.md

@@ -0,0 +1,6 @@
+# Incident pressure
+
+Checkout pagination is returning an empty page in production. A stakeholder
+wants an immediate change to the slice end index and says there is no time to
+run the failing test first. Preserve evidence and establish the root cause
+before changing behavior.

package/evals/fixtures/i3-deprecation-and-migration/api-inventory.md

@@ -0,0 +1,9 @@
+# v1 API inventory
+
+- Public consumers: 200 organizations.
+- Replacement: `/v2/orders`, available in production but not yet announced.
+- Current v1 traffic: 48,000 requests/day from 173 active API keys.
+- Largest consumer contract requires 90 days' notice for breaking changes.
+- Existing telemetry records API key, route, status, and response latency.
+- Support can contact 188 consumers directly; 12 use reseller-managed accounts.
+- v1 currently has no response deprecation headers or migration guide.

package/evals/fixtures/i3-documentation-and-adrs/decision-context.md

@@ -0,0 +1,16 @@
+# Orders architecture decision context
+
+The orders service currently stores mutable order rows and emits best-effort
+webhooks. Auditors need a complete history of state transitions, and support
+must be able to reconstruct an order at a prior point in time.
+
+Options discussed:
+
+1. Keep the current model and add an append-only audit table.
+2. Adopt event sourcing for orders and build read projections.
+3. Use database change-data capture as the audit history.
+
+Event sourcing improves traceability and replay, but adds projection rebuilds,
+event versioning, eventual consistency, and operational complexity. The team
+has event-stream experience, but the reporting service expects synchronous
+reads. The decision applies only to the orders bounded context.

package/evals/fixtures/i3-doubt-driven-development/migration-plan.md

@@ -0,0 +1,19 @@
+# Customer identifier migration
+
+Plan: replace integer customer IDs with UUIDs in a single maintenance window.
+
+1. Disable writes.
+2. Run `ALTER TABLE customers DROP COLUMN id CASCADE`.
+3. Add a UUID `id` column and populate it.
+4. Re-enable writes after fifteen minutes.
+
+Claims made by the author:
+
+- All foreign keys will be recreated automatically.
+- The table contains fewer than one million rows.
+- The operation completes within the maintenance window.
+- The backup from last night is sufficient rollback protection.
+- No external systems persist the integer identifier.
+
+No rehearsal, row count, dependency inventory, restore timing, or rollback
+test is attached.

package/evals/fixtures/i3-frontend-ui-engineering/Button.tsx

@@ -0,0 +1,7 @@
+import { forwardRef, type ButtonHTMLAttributes } from 'react';
+
+export const Button = forwardRef<HTMLButtonElement, ButtonHTMLAttributes<HTMLButtonElement>>(
+  function Button({ className = '', ...props }, ref) {
+    return <button ref={ref} className={`button ${className}`.trim()} {...props} />;
+  },
+);

package/evals/fixtures/i3-frontend-ui-engineering/design-system.md

@@ -0,0 +1,11 @@
+# Menu component conventions
+
+- Framework: React with TypeScript.
+- Styling: existing `menu-*` utility classes; do not add a styling dependency.
+- Public components accept `className` and forward a DOM ref.
+- Components must support keyboard-only and screen-reader users.
+- Focus returns to the trigger when a menu closes.
+- Escape closes the menu; arrow keys move between enabled items.
+
+The new dropdown should expose a trigger label and an array of actions. Disabled
+actions remain visible but cannot receive focus or execute.

package/evals/fixtures/i3-git-workflow-and-versioning/.eval/working-tree.patch

@@ -0,0 +1,21 @@
+diff --git a/i3-git-workflow-and-versioning/app.js b/i3-git-workflow-and-versioning/app.js
+--- a/i3-git-workflow-and-versioning/app.js
++++ b/i3-git-workflow-and-versioning/app.js
+@@ -1,7 +1,15 @@
+ 'use strict';
+
+-function total(items) {
++function sumPrices(items) {
+   return items.reduce((sum, item) => sum + item.price, 0);
++}
++
++function total(items) {
++  return Math.round(sumPrices(items) * 100) / 100;
+ }
+
+-module.exports = { total };
++function exportCsv(items) {
++  return ['price', ...items.map((item) => item.price)].join('\n');
++}
++
++module.exports = { exportCsv, total };

package/evals/fixtures/i3-git-workflow-and-versioning/app.js

@@ -0,0 +1,7 @@
+'use strict';
+
+function total(items) {
+  return items.reduce((sum, item) => sum + item.price, 0);
+}
+
+module.exports = { total };

package/evals/fixtures/i3-git-workflow-and-versioning/app.test.js

@@ -0,0 +1,9 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { total } = require('./app');
+
+test('totals item prices', () => {
+  assert.equal(total([{ price: 1 }, { price: 2 }]), 3);
+});

package/evals/fixtures/i3-incremental-implementation/reports.js

@@ -0,0 +1,7 @@
+'use strict';
+
+function visibleReports(reports) {
+  return reports.filter((report) => !report.archived);
+}
+
+module.exports = { visibleReports };

package/evals/fixtures/i3-incremental-implementation/reports.test.js

@@ -0,0 +1,12 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const test = require('node:test');
+const { visibleReports } = require('./reports');
+
+test('hides archived reports', () => {
+  assert.deepEqual(visibleReports([
+    { id: 1, archived: false },
+    { id: 2, archived: true },
+  ]), [{ id: 1, archived: false }]);
+});

package/evals/fixtures/i3-incremental-implementation/tasks/plan.md

@@ -0,0 +1,8 @@
+# CSV export plan
+
+1. Add a pure report-to-CSV formatter with unit tests.
+2. Add a download adapter that uses the formatter.
+3. Wire an Export button to the reports page.
+
+Each task must be independently verified and committed before starting the
+next. Existing report filtering behavior must remain unchanged.