@givolt/i3-composer-agent 1.0.0 → 2.0.0

package/references/definition-of-done.md

@@ -1,6 +1,6 @@
 # Definition of Done
 
-A standing, project-wide bar that every change must clear before it counts as done. Unlike acceptance criteria, which vary per task and answer "did we build the right thing?", the Definition of Done is the same every time and answers "is this finished to our standard?". Use it as the final gate in `planning-and-task-breakdown`, `incremental-implementation`, and `shipping-and-launch`.
+A standing, project-wide bar that every change must clear before it counts as done. Unlike acceptance criteria, which vary per task and answer "did we build the right thing?", the Definition of Done is the same every time and answers "is this finished to our standard?". Use it as the final gate in `i3-planning-and-task-breakdown`, `i3-incremental-implementation`, and `i3-shipping-and-launch`.
 
 ## Definition of Done vs. Acceptance Criteria
 
@@ -32,7 +32,7 @@ Apply this to every change before declaring it done.
 - [ ] Changes are scoped to the task; no unrelated refactors snuck in
 - [ ] Linting and formatting pass
 
-The depth behind these items lives in `code-review-and-quality` (the five-axis review) and `code-simplification` (reducing complexity without changing behavior).
+The depth behind these items lives in `i3-code-review-and-quality` (the five-axis review) and `i3-code-simplification` (reducing complexity without changing behavior).
 
 ### Integration
 - [ ] Change works with the rest of the system, not just in isolation
@@ -41,20 +41,20 @@ The depth behind these items lives in `code-review-and-quality` (the five-axis r
 
 ### Documentation
 - [ ] Public interfaces, APIs, and user-facing behavior are documented
-- [ ] Architectural decisions worth preserving are recorded (see `documentation-and-adrs`)
+- [ ] Architectural decisions worth preserving are recorded (see `i3-documentation-and-adrs`)
 - [ ] Documentation describes the current state in timeless language, not the change history
 
 ### Ship-readiness
-- [ ] Security implications reviewed for any untrusted input, auth, or data handling (see `security-and-hardening`)
-- [ ] Observability in place for new critical paths (logs, metrics, traces) (see `observability-and-instrumentation`)
-- [ ] Rollback path exists for anything risky (see `shipping-and-launch`)
+- [ ] Security implications reviewed for any untrusted input, auth, or data handling (see `i3-security-and-hardening`)
+- [ ] Observability in place for new critical paths (logs, metrics, traces) (see `i3-observability-and-instrumentation`)
+- [ ] Rollback path exists for anything risky (see `i3-shipping-and-launch`)
 - [ ] The human has reviewed and approved before merge or deploy
 
 ## How to Apply
 
 - **Per task**: confirm the Correctness and Quality sections before checking the task off.
 - **Per feature**: confirm Integration and Documentation before considering the feature complete.
-- **Per release**: the full checklist is the floor; `shipping-and-launch` adds the deploy-specific gates on top.
+- **Per release**: the full checklist is the floor; `i3-shipping-and-launch` adds the deploy-specific gates on top.
 
 Tailor the list to the project once, then reuse it unchanged. A Definition of Done that is renegotiated every sprint is not a Definition of Done.
 

package/references/observability-checklist.md

@@ -1,6 +1,6 @@
 # Observability Checklist
 
-Quick reference for instrumenting production code. Use alongside the `observability-and-instrumentation` skill.
+Quick reference for instrumenting production code. Use alongside the `i3-observability-and-instrumentation` skill.
 
 ## Table of Contents
 
@@ -28,7 +28,7 @@ Telemetry without a question is noise. Before instrumenting anything:
 - [ ] Correlation ID is propagated on every outbound call and async boundary (HTTP headers, queue metadata)
 - [ ] Any log stream written by more than one entry point (scheduler, replay endpoint, manual run) carries an entry-point field, set where the run starts and propagated alongside the correlation ID
 - [ ] Log levels are consistent: `error` = invariant broken, someone may act; `warn` = degraded but handled; `info` = significant business event; `debug` = off in production
-- [ ] No secrets, tokens, passwords, or unredacted PII in any log line (hard rule from `security-and-hardening`)
+- [ ] No secrets, tokens, passwords, or unredacted PII in any log line (hard rule from `i3-security-and-hardening`)
 - [ ] Fields are allowlisted — no whole request/response bodies, no auth headers
 - [ ] External service calls logged with metadata only: endpoint, status, latency, attempt count, sanitized identifiers
 - [ ] Actual log output spot-checked: structured fields, not `[object Object]`
@@ -89,4 +89,4 @@ Before a feature ships to production, all of the following are true:
 - [ ] A request can be traced across every service it touches
 - [ ] On-call knows where the runbooks are
 
-For launch-day monitoring sequence and rollback triggers, see the `shipping-and-launch` skill.
+For launch-day monitoring sequence and rollback triggers, see the `i3-shipping-and-launch` skill.

package/references/orchestration-patterns.md

@@ -32,12 +32,12 @@ user → code-reviewer → report → user
 A slash command that wraps one persona with the project's skills. Saves the user from re-explaining the workflow every time.
 
 ```
-/review → code-reviewer (with code-review-and-quality skill) → report
+/i3-review → code-reviewer (with i3-code-review-and-quality skill) → report
 ```
 
 **Use when:** the same single-persona invocation happens repeatedly with the same setup.
 
-**Examples in this repo:** `/review`, `/test`, `/code-simplify`.
+**Examples in this repo:** `/i3-review`, `/i3-test`, `/i3-code-simplify`.
 
 **Cost:** same as direct invocation. The slash command is just a saved prompt.
 
@@ -51,7 +51,7 @@ Multiple personas operate on the same input concurrently, each producing an inde
 
 ```
                     ┌─→ code-reviewer    ─┐
-/ship → fan out  ───┼─→ security-auditor ─┤→ merge → go/no-go + rollback
+/i3-ship → fan out  ───┼─→ security-auditor ─┤→ merge → go/no-go + rollback
                     └─→ test-engineer    ─┘
 ```
 
@@ -61,7 +61,7 @@ Multiple personas operate on the same input concurrently, each producing an inde
 - The merge step is small enough to stay in the main context
 - Wall-clock latency matters
 
-**Examples in this repo:** `/ship`.
+**Examples in this repo:** `/i3-ship`.
 
 **Cost:** N parallel sub-agent contexts + one merge turn. Higher than direct invocation, but faster wall-clock and produces better reports because each sub-agent stays focused on its single perspective.
 
@@ -80,7 +80,7 @@ If any answer is "no," fall back to direct invocation or a single-persona comman
 The user runs slash commands in a defined order, carrying context (or commit history) between them. There is no orchestrator agent — the user IS the orchestrator.
 
 ```
-user runs:  /spec  →  /plan  →  /build  →  /test  →  /review  →  /ship
+user runs:  /i3-spec  →  /i3-plan  →  /i3-build  →  /i3-test  →  /i3-review  →  /i3-ship
 ```
 
 **Use when:** the workflow has dependencies (each step needs the previous step's output) and human judgment between steps adds value.
@@ -134,7 +134,7 @@ Claude Code has two parallelism primitives. Pattern 3 (parallel fan-out with mer
 | Status | Stable | Experimental — requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` |
 | Cost | Lower | Higher — each teammate is a separate Claude instance |
 
-**The personas in this repo work in both modes.** When spawned as subagents (e.g. by `/ship`), they report findings to the main session. When spawned as teammates (`Spawn a teammate using the security-auditor agent type…`), they can challenge each other's findings directly. The persona definition is the same; only the spawning context changes.
+**The personas in this repo work in both modes.** When spawned as subagents (e.g. by `/i3-ship`), they report findings to the main session. When spawned as teammates (`Spawn a teammate using the security-auditor agent type…`), they can challenge each other's findings directly. The persona definition is the same; only the spawning context changes.
 
 One subtlety: the `skills` and `mcpServers` frontmatter fields in a persona are honored when it runs as a subagent but **ignored when it runs as a teammate** — teammates load skills and MCP servers from your project and user settings, the same as a regular session. If a persona depends on a specific skill or MCP server being loaded, configure it at the session level so it's available in both modes.
 
@@ -167,13 +167,13 @@ The fields that DO work in plugin agents are: `name`, `description`, `tools`, `d
 
 ### Spawning multiple subagents in parallel
 
-In Claude Code, parallel fan-out (Pattern 3) requires issuing **multiple Agent tool calls in a single assistant turn**. Sequential turns serialize execution. `/ship` calls this out explicitly. Any new orchestrator command should do the same.
+In Claude Code, parallel fan-out (Pattern 3) requires issuing **multiple Agent tool calls in a single assistant turn**. Sequential turns serialize execution. `/i3-ship` calls this out explicitly. Any new orchestrator command should do the same.
 
 ---
 
 ## Worked example: Agent Teams for competing-hypothesis debugging
 
-This example shows when to reach for **Agent Teams** instead of `/ship`'s subagent fan-out. The two patterns look similar from a distance — both spawn the same three personas — but the value comes from a different place.
+This example shows when to reach for **Agent Teams** instead of `/i3-ship`'s subagent fan-out. The two patterns look similar from a distance — both spawn the same three personas — but the value comes from a different place.
 
 ### The scenario
 
@@ -186,19 +186,19 @@ Plausible root causes (mutually exclusive, all fit the symptoms):
 3. A missing index on a query that scales with cart size
 4. A flaky third-party API where the SDK retries silently before timing out
 
-A single agent will pick the first plausible theory and stop investigating. A `/ship`-style subagent fan-out would have each persona report independently — but their reports never meet, so nothing rules out the wrong theories.
+A single agent will pick the first plausible theory and stop investigating. A `/i3-ship`-style subagent fan-out would have each persona report independently — but their reports never meet, so nothing rules out the wrong theories.
 
 This is exactly the case the Agent Teams docs describe: *"With multiple independent investigators actively trying to disprove each other, the theory that survives is much more likely to be the actual root cause."*
 
-### Why this is *not* a `/ship` job
+### Why this is *not* a `/i3-ship` job
 
-| | `/ship` (subagents) | Agent Teams |
+| | `/i3-ship` (subagents) | Agent Teams |
 |--|--------------------|-------------|
 | Sub-agents see | The same diff, different lenses | A shared task list, each other's messages |
 | Output | Three independent reports → one merge | Adversarial debate → consensus root cause |
 | Right when | You want a verdict on a known artifact | You want to *find* the artifact among hypotheses |
 
-`/ship` is a verdict; Agent Teams is an investigation.
+`/i3-ship` is a verdict; Agent Teams is an investigation.
 
 ### Setup (one-time, per-environment)
 
@@ -262,7 +262,7 @@ Always cleanup through the lead, not a teammate (per the docs: teammates lack fu
 
 ### Cost expectation
 
-Three Sonnet teammates running for ~10–15 minutes of investigation costs noticeably more than the same three personas spawned as subagents by `/ship`. The justification is *quality of conclusion* — for production debugging where the wrong fix is expensive, the extra tokens are a bargain. For a routine PR review, stick with `/ship`.
+Three Sonnet teammates running for ~10–15 minutes of investigation costs noticeably more than the same three personas spawned as subagents by `/i3-ship`. The justification is *quality of conclusion* — for production debugging where the wrong fix is expensive, the extra tokens are a bargain. For a routine PR review, stick with `/i3-ship`.
 
 ### Anti-pattern in this scenario
 
@@ -270,7 +270,7 @@ Do **not** rebuild this as a `/debug` slash command that fans out subagents. Sub
 
 ### When *not* to use Agent Teams
 
-- Production-bound verdict on a known diff → use `/ship` (subagents).
+- Production-bound verdict on a known diff → use `/i3-ship` (subagents).
 - One specialist perspective on one artifact → direct persona invocation.
 - Sequential lifecycle (spec → plan → build) → user-driven slash commands (Pattern 4).
 - Read-heavy research with a small digest → built-in `Explore` subagent.
@@ -292,7 +292,7 @@ A persona whose job is to decide which other persona to call.
 **Why it fails:**
 - Pure routing layer with no domain value
 - Adds two paraphrasing hops → information loss + roughly 2× token cost
-- The user already knew they wanted a review; they could have called `/review` directly
+- The user already knew they wanted a review; they could have called `/i3-review` directly
 - Replicates the work that slash commands and intent mapping in `AGENTS.md` already do
 
 **What to do instead:** add or refine slash commands. Document intent → command mapping in `AGENTS.md`.
@@ -315,7 +315,7 @@ A `code-reviewer` that internally invokes `security-auditor` when it sees auth c
 
 ### C. Sequential orchestrator that paraphrases
 
-An agent that calls `/spec`, then `/plan`, then `/build`, etc. on the user's behalf.
+An agent that calls `/i3-spec`, then `/i3-plan`, then `/i3-build`, etc. on the user's behalf.
 
 **Why it fails:**
 - Loses the human checkpoints that catch wrong-direction work
@@ -329,7 +329,7 @@ An agent that calls `/spec`, then `/plan`, then `/build`, etc. on the user's beh
 
 ### D. Deep persona trees
 
-`/ship` calls a `pre-ship-coordinator` that calls a `quality-coordinator` that calls `code-reviewer`.
+`/i3-ship` calls a `pre-ship-coordinator` that calls a `quality-coordinator` that calls `code-reviewer`.
 
 **Why it fails:**
 - Each layer adds latency and tokens with no decision value

package/references/performance-checklist.md

@@ -1,6 +1,6 @@
 # Performance Checklist
 
-Quick reference checklist for web application performance. Use alongside the `performance-optimization` skill.
+Quick reference checklist for web application performance. Use alongside the `i3-performance-optimization` skill.
 
 ## Table of Contents
 
@@ -132,7 +132,7 @@ When TTFB is slow (> 800ms), check each component in DevTools Network waterfall:
 
 ## Caching Strategies
 
-The decision material (which layer, which invalidation strategy, what never to cache) lives in the `performance-optimization` skill. This section covers the read/write patterns and the checklist.
+The decision material (which layer, which invalidation strategy, what never to cache) lives in the `i3-performance-optimization` skill. This section covers the read/write patterns and the checklist.
 
 ### Read and write patterns
 

package/references/security-checklist.md

@@ -1,6 +1,6 @@
 # Security Checklist
 
-Quick reference for web application security. Use alongside the `security-and-hardening` skill.
+Quick reference for web application security. Use alongside the `i3-security-and-hardening` skill.
 
 ## Table of Contents
 

package/references/testing-patterns.md

@@ -1,6 +1,6 @@
 # Testing Patterns Reference (JavaScript/TypeScript)
 
-Quick reference of JavaScript/TypeScript testing patterns — Jest, React Testing Library, Supertest, and Playwright — illustrating the universal principles from the `test-driven-development` skill. The principles (Arrange-Act-Assert, naming, mock discipline, anti-patterns) apply in any ecosystem; the syntax and tooling shown here are JS/TS-specific. In another stack, follow the same principles with the repository's own test framework and commands.
+Quick reference of JavaScript/TypeScript testing patterns — Jest, React Testing Library, Supertest, and Playwright — illustrating the universal principles from the `i3-test-driven-development` skill. The principles (Arrange-Act-Assert, naming, mock discipline, anti-patterns) apply in any ecosystem; the syntax and tooling shown here are JS/TS-specific. In another stack, follow the same principles with the repository's own test framework and commands.
 
 ## Table of Contents
 

package/scripts/floor-guard-reference-test.js

@@ -2,7 +2,7 @@
 
 'use strict';
 
-// Contract test for skills/constraint-driven-development/references/floor-guard.md.
+// Contract test for skills/i3-constraint-driven-development/references/floor-guard.md.
 // The fenced `js` block is extracted unchanged and run, with real git, against small
 // fixtures: each is a fresh repository with one source file, one test file and a
 // CONSTRAINTS.md carrying a floor bullet, a coverage minimum, a bundle maximum and an
@@ -16,7 +16,7 @@ const { spawnSync } = require('node:child_process');
 const { after, before, test } = require('node:test');
 
 const REFERENCE = path.join(
-  __dirname, '..', 'skills', 'constraint-driven-development', 'references', 'floor-guard.md',
+  __dirname, '..', 'skills', 'i3-constraint-driven-development', 'references', 'floor-guard.md',
 );
 const CONSTRAINTS = [
   '# Constraints',

package/scripts/lib/skill-lint.js

@@ -85,6 +85,8 @@ const REQUIRED_SECTIONS = [
 // cannot bypass the validator by editing their own skill file.
 // Every entry must have a documented reason.
 const SECTION_EXEMPT_SKILLS = {
+  'i3-using-agent-skills': 'Branded alias of the reviewed upstream meta-skill.',
+  'i3-idea-refine': 'Branded alias of the reviewed upstream legacy structure.',
   'using-agent-skills': 'Meta-skill — orchestrates other skills; When-to-Use and Verification are not applicable to a routing document.',
   'idea-refine':        'Legacy structure predating skill-anatomy.md — uses How-It-Works/Usage/Anti-patterns instead of standard headings. Tracked for conformance in https://github.com/addyosmani/agent-skills/issues',
 };

package/scripts/run-evals-test.js

@@ -608,13 +608,13 @@ test('accepted grading omits run key when no metadata is provided', () => {
 });
 
 test('materializes a git baseline and applies a working-tree patch', () => {
-  const workspace = materializeWorkspace({ files: ['git-workflow-and-versioning'] });
+  const workspace = materializeWorkspace({ files: ['i3-git-workflow-and-versioning'] });
   try {
     const status = spawnSync('git', ['status', '--short'], { cwd: workspace, encoding: 'utf8' });
     const commits = spawnSync('git', ['rev-list', '--count', 'HEAD'], { cwd: workspace, encoding: 'utf8' });
 
     assert.equal(status.status, 0, status.stdout + status.stderr);
-    assert.match(status.stdout, / M git-workflow-and-versioning\/app\.js/);
+    assert.match(status.stdout, / M i3-git-workflow-and-versioning\/app\.js/);
     assert.equal(commits.stdout.trim(), '1');
     assert.equal(fs.existsSync(path.join(workspace, '.eval')), false);
   } finally {

package/scripts/validate-artifact-paths-test.js

@@ -45,8 +45,8 @@ test('passes when producers and consumers use the canonical artifact paths', ()
   writeFile(root, '.claude/commands/spec.md', 'Save the spec as `SPEC.md` in the project root.\n');
   writeFile(root, '.claude/commands/plan.md', 'Save the plan to `tasks/plan.md` and task list to `tasks/todo.md`.\n');
   writeFile(root, '.claude/commands/build.md', 'Look for a spec at `SPEC.md`, `docs/SPEC.md`, or under `spec/`. Require `tasks/plan.md`.\n');
-  writeFile(root, 'skills/spec-driven-development/SKILL.md', 'Save the plan to `tasks/plan.md` and the task list to `tasks/todo.md`.\n');
-  writeFile(root, 'skills/planning-and-task-breakdown/SKILL.md', 'Save to `tasks/plan.md` and `tasks/todo.md`.\n');
+  writeFile(root, 'skills/i3-spec-driven-development/SKILL.md', 'Save the plan to `tasks/plan.md` and the task list to `tasks/todo.md`.\n');
+  writeFile(root, 'skills/i3-planning-and-task-breakdown/SKILL.md', 'Save to `tasks/plan.md` and `tasks/todo.md`.\n');
 
   const result = run(root);
 
@@ -94,7 +94,7 @@ test('ignores non-artifact markdown references (no false positives)', () => {
   const root = makeSandbox();
   writeFile(
     root,
-    'skills/spec-driven-development/SKILL.md',
+    'skills/i3-spec-driven-development/SKILL.md',
     'See `SKILL.md` and `references/testing-patterns.md`. Save the plan to `tasks/plan.md`.\n',
   );
 

package/scripts/validate-artifact-paths.js

@@ -60,8 +60,8 @@ const GUARDED_FILES = [
   'commands/planning.toml',
   'commands/build.toml',
   // Skills the commands invoke
-  'skills/spec-driven-development/SKILL.md',
-  'skills/planning-and-task-breakdown/SKILL.md',
+  'skills/i3-spec-driven-development/SKILL.md',
+  'skills/i3-planning-and-task-breakdown/SKILL.md',
   // Docs that tell users where the artifacts live
   'docs/getting-started.md',
   'docs/adoption-guide.md',
@@ -74,6 +74,8 @@ const GUARDED_FILES = [
 // drifted spec.md are both caught, then compared against the allowlist.
 const ARTIFACT_RE = /(?:[A-Za-z0-9._[\]-]+\/)*(?:spec|plan|todo)\.md/gi;
 
+GUARDED_FILES.push(...GUARDED_FILES.filter(relative => /(?:^|\/)commands\//.test(relative)).map(relative => relative.replace(/(commands\/)([^/]+)(\.md|\.toml)$/, '$1i3-$2$3')));
+
 function findViolations(relPath) {
   const abs = path.join(ROOT, relPath);
   if (!fs.existsSync(abs)) return null; // skipped

package/scripts/validate-brand.cjs

@@ -9,7 +9,7 @@ const brand = require('../rebrand/brand.json');
 const pkg = require('../package.json');
 const upstream = require('../rebrand/upstream.json');
 const { validateCatalog } = require('../rebrand/catalog.cjs');
-validateCatalog(root, upstream);
+validateCatalog(root, upstream, { branded: true });
 function json(relative) { return JSON.parse(fs.readFileSync(path.join(root, relative), 'utf8')); }
 assert.equal(pkg.name, brand.npmName);
 assert.equal(pkg.version, brand.releaseVersion);
@@ -31,13 +31,13 @@ for (const relative of ['.claude-plugin/marketplace.json', '.agents/plugins/mark
 assert.ok(json('.codex-plugin/plugin.json').interface.shortDescription.length <= 30);
 const skills = fs.readdirSync(path.join(root, 'skills')).filter(name => fs.existsSync(path.join(root, 'skills', name, 'SKILL.md')));
 assert.equal(skills.length, upstream.skills.length, 'brand conversion must preserve the reviewed upstream skills');
-assert.ok(skills.includes('using-agent-skills'), 'meta-skill ID must remain stable');
+assert.ok(skills.includes('i3-using-agent-skills'), 'meta-skill ID must use the branded prefix');
 const commands = fs.readdirSync(path.join(root, '.claude/commands')).filter(name => name.endsWith('.md'));
 assert.equal(commands.length, upstream.commands.length, 'brand conversion must preserve the reviewed upstream commands');
 for (const command of commands) {
   const body = fs.readFileSync(path.join(root, '.claude/commands', command), 'utf8');
   assert.ok(!body.includes('agent-skills:'), `${command}: stale plugin namespace`);
-  for (const match of body.matchAll(/i3-composer-agent:([a-z-]+)/g)) assert.ok(skills.includes(match[1]), `${command}: unknown skill ${match[1]}`);
+  for (const match of body.matchAll(/(?<!\/)i3-composer-agent:([a-z0-9-]+)/g)) assert.ok(skills.includes(match[1]), `${command}: unknown skill ${match[1]}`);
 }
 for (const relative of pkg.i3ComposerAgent.pluginFiles) assert.ok(fs.existsSync(path.join(root, relative)), `bundle is missing ${relative}`);
 assert.match(fs.readFileSync(path.join(root, 'LICENSE'), 'utf8'), /Copyright \(c\) 2025 Addy Osmani/);

package/scripts/validate-commands.js

@@ -46,6 +46,7 @@ const DIRS = {
 // Key = Claude stem, value = TOML stem.
 const NAME_MAP = {
   plan: 'planning',
+  'i3-plan': 'i3-planning',
 };
 const NAME_MAP_REVERSE = Object.fromEntries(
   Object.entries(NAME_MAP).map(([k, v]) => [v, k])

package/scripts/validate-reference-links-test.js

@@ -47,7 +47,7 @@ test('passes when a skill reaches the shared checklist two levels up', () => {
   writeFile(root, 'references/definition-of-done.md', '# Definition of Done\n');
   writeFile(
     root,
-    'skills/using-agent-skills/SKILL.md',
+    'skills/i3-using-agent-skills/SKILL.md',
     'See `../../references/definition-of-done.md`.\n'
   );
 
@@ -64,7 +64,7 @@ test('fails when a skill links the shared checklist as if it were colocated', ()
   writeFile(root, 'references/definition-of-done.md', '# Definition of Done\n');
   writeFile(
     root,
-    'skills/using-agent-skills/SKILL.md',
+    'skills/i3-using-agent-skills/SKILL.md',
     'See `references/definition-of-done.md`.\n'
   );
 
@@ -74,7 +74,7 @@ test('fails when a skill links the shared checklist as if it were colocated', ()
   assert.match(result.stdout, /1 skills checked — 1 error\(s\) — FAILED/);
   assert.match(
     result.stdout,
-    /L1: references\/definition-of-done\.md — resolves to skills\/using-agent-skills\/references\/definition-of-done\.md/
+    /L1: references\/definition-of-done\.md — resolves to skills\/i3-using-agent-skills\/references\/definition-of-done\.md/
   );
   assert.match(result.stdout, /use `\.\.\/\.\.\/references\/<file>\.md`/);
 });
@@ -82,7 +82,7 @@ test('fails when a skill links the shared checklist as if it were colocated', ()
 test('checks markdown link syntax, not just backtick mentions', () => {
   const root = makeSandbox();
   writeFile(root, 'references/definition-of-done.md', '# Definition of Done\n');
-  writeFile(root, 'skills/using-agent-skills/SKILL.md', 'See [DoD](references/definition-of-done.md).\n');
+  writeFile(root, 'skills/i3-using-agent-skills/SKILL.md', 'See [DoD](references/definition-of-done.md).\n');
 
   const result = run(root);
 
@@ -193,7 +193,7 @@ test('counts errors from SKILL.md and its reference files together', () => {
 test('fails when a link points at a checklist that no longer exists', () => {
   const root = makeSandbox();
   writeFile(root, 'references/definition-of-done.md', '# Definition of Done\n');
-  writeFile(root, 'skills/shipping-and-launch/SKILL.md', 'See `../../references/renamed.md`.\n');
+  writeFile(root, 'skills/i3-shipping-and-launch/SKILL.md', 'See `../../references/renamed.md`.\n');
 
   const result = run(root);
 
@@ -209,11 +209,11 @@ test('ignores paths that are not references/ links', () => {
   writeFile(root, 'references/definition-of-done.md', '# Definition of Done\n');
   writeFile(
     root,
-    'skills/planning-and-task-breakdown/SKILL.md',
+    'skills/i3-planning-and-task-breakdown/SKILL.md',
     [
       'Save the task list to `tasks/todo.md` and the plan to `tasks/plan.md`.',
       'Record findings in `PERF.md` or `docs/ideas/[idea-name].md`.',
-      'Related: `skills/incremental-implementation/SKILL.md`.',
+      'Related: `skills/i3-incremental-implementation/SKILL.md`.',
       'See `../../references/definition-of-done.md`.',
       '',
     ].join('\n')
@@ -231,7 +231,7 @@ test('reports every unresolvable link, not just the first per skill', () => {
   writeFile(root, 'references/performance-checklist.md', '# Performance\n');
   writeFile(
     root,
-    'skills/code-review-and-quality/SKILL.md',
+    'skills/i3-code-review-and-quality/SKILL.md',
     ['See `references/security-checklist.md`.', 'And `references/performance-checklist.md`.', ''].join('\n')
   );
 
@@ -246,7 +246,7 @@ test('a link inside a fenced block is an example, not a link to resolve', () =>
   writeFile(root, 'references/definition-of-done.md', '# DoD\n');
   writeFile(
     root,
-    'skills/using-agent-skills/SKILL.md',
+    'skills/i3-using-agent-skills/SKILL.md',
     [
       'Shared checklists live two levels up:',
       '',
@@ -271,7 +271,7 @@ test('fence exemption follows CommonMark rather than a bare ``` match', () => {
   const root = makeSandbox();
   writeFile(
     root,
-    'skills/using-agent-skills/SKILL.md',
+    'skills/i3-using-agent-skills/SKILL.md',
     [
       '~~~markdown',
       '[a](references/missing-a.md)',
@@ -296,7 +296,7 @@ test('a real broken link outside any fence is still reported', () => {
   const root = makeSandbox();
   writeFile(
     root,
-    'skills/using-agent-skills/SKILL.md',
+    'skills/i3-using-agent-skills/SKILL.md',
     [
       '```markdown',
       '[shown as an example](references/example-only.md)',

package/scripts/validate-reference-links.js

@@ -9,7 +9,7 @@
  * the skill's own directory, which is two levels below the root. All 18 links
  * across 11 skills resolved to files that do not exist, in the repo and in
  * every plugin-install layout (~/.claude/plugins/cache/..., ~/.codex/...).
- * Agents that followed the guidance — for example using-agent-skills pointing
+ * Agents that followed the guidance — for example i3-using-agent-skills pointing
  * at the Definition of Done — hit a file-not-found and stalled.
  *
  * Nothing else in CI catches this: validate-artifact-paths.js is scoped to

package/skills/{api-and-interface-design → i3-api-and-interface-design}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: api-and-interface-design
+name: i3-api-and-interface-design
 description: Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
 ---
 
@@ -27,7 +27,7 @@ This means: every public behavior — including undocumented quirks, error messa
 
 - **Be intentional about what you expose.** Every observable behavior is a potential commitment.
 - **Don't leak implementation details.** If users can observe it, they will depend on it.
-- **Plan for deprecation at design time.** See `deprecation-and-migration` for how to safely remove things users depend on.
+- **Plan for deprecation at design time.** See `i3-deprecation-and-migration` for how to safely remove things users depend on.
 - **Tests are not enough.** Even with perfect contract tests, Hyrum's Law means "safe" changes can break real users who depend on undocumented behavior.
 
 ### The One-Version Rule

package/skills/{browser-testing-with-devtools → i3-browser-testing-with-devtools}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: browser-testing-with-devtools
+name: i3-browser-testing-with-devtools
 description: Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
 ---
 

package/skills/{ci-cd-and-automation → i3-ci-cd-and-automation}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: ci-cd-and-automation
+name: i3-ci-cd-and-automation
 description: Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
 ---
 
@@ -186,7 +186,7 @@ Agent fixes → pushes → CI runs again
 ```
 Lint failure → Agent runs `npm run lint --fix` and commits
 Type error  → Agent reads the error location and fixes the type
-Test failure → Agent follows debugging-and-error-recovery skill
+Test failure → Agent follows i3-debugging-and-error-recovery skill
 Build error → Agent checks config and dependencies
 ```
 

package/skills/{code-review-and-quality → i3-code-review-and-quality}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: code-review-and-quality
+name: i3-code-review-and-quality
 description: Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Use when asked to review a diff or a pull request, even when the diff is pasted inline.
 ---
 
@@ -63,7 +63,7 @@ Does the change fit the system's design?
 
 ### 4. Security
 
-For detailed security guidance, see `security-and-hardening`. Does the change introduce vulnerabilities?
+For detailed security guidance, see `i3-security-and-hardening`. Does the change introduce vulnerabilities?
 
 - Is user input validated and sanitized?
 - Are secrets kept out of code, logs, and version control?
@@ -76,7 +76,7 @@ For detailed security guidance, see `security-and-hardening`. Does the change in
 
 ### 5. Performance
 
-For detailed profiling and optimization, see `performance-optimization`. Does the change introduce performance problems?
+For detailed profiling and optimization, see `i3-performance-optimization`. Does the change introduce performance problems?
 
 - Any N+1 query patterns?
 - Any unbounded loops or unconstrained data fetching?
@@ -161,7 +161,7 @@ Tests reveal intent and coverage:
 - Would the tests catch a regression if the code changed?
 ```
 
-Answer the last question by experiment, not by reading. Invert one condition the change adds (drop a negation, swap `&&` for `||`), run the suite, then restore the file from a copy. A mutation that stays green is a finding: name the test case that is missing. For a project-wide mutation score, see `constraint-driven-development`.
+Answer the last question by experiment, not by reading. Invert one condition the change adds (drop a negation, swap `&&` for `||`), run the suite, then restore the file from a copy. A mutation that stays green is a finding: name the test case that is missing. For a project-wide mutation score, see `i3-constraint-driven-development`.
 
 ### Step 3: Review the Implementation
 
@@ -299,7 +299,7 @@ Part of code review is dependency review:
 4. **Mind the transitive graph.** Most installed packages are ones nobody chose directly. Review the lockfile diff, not just `package.json`; a single direct bump can pull in dozens of indirect changes.
 5. **Keep the lockfile honest.** Commit it, review its diff, and never hand-edit it. The lockfile is the thing that actually pins what ships.
 
-For triaging `npm audit` findings and supply-chain risk (typosquatting, compromised maintainers), follow the `security-and-hardening` skill — this section covers the upgrade *workflow*, that one covers the security verdict.
+For triaging `npm audit` findings and supply-chain risk (typosquatting, compromised maintainers), follow the `i3-security-and-hardening` skill — this section covers the upgrade *workflow*, that one covers the security verdict.
 
 ## The Review Checklist
 

package/skills/{code-simplification → i3-code-simplification}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: code-simplification
+name: i3-code-simplification
 description: Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
 ---