feat: v21 improve

.github/CHANGELOG.md

@@ -21,11 +21,11 @@ Use this format for new updates:
 
 ## 2026-06-02
 
-- Added `internal-gateway-idea-brainstorming` as a visible fourth gateway skill and thin Copilot wrapper agent, owning substantive idea definition, guided decision interview, convergence, Definition Brief, mandatory critical pass, and validated handoff before operational planning.
+- Added `internal-gateway-idea` as a visible fourth gateway skill and thin Copilot wrapper agent, owning substantive idea definition, guided decision interview, convergence, Definition Brief, mandatory critical pass, and validated handoff before operational planning.
 - Absorbed and retired `internal-idea-define-advisor`, moving its useful owner-map and question-bank concepts into the new gateway bundle without a compatibility stub or alias.
 - Narrowed `internal-gateway-operational-flow` to delegate unresolved idea work visibly to the new gateway and consume validated Definition Brief handoffs for `plan` without repeating ideation or its critical pass.
 - Added guided decision interview semantics: evidence-first discovery, iterative numbered question blocks through `grill-me`, visible defaults, compact decision ledger, proportional depth, and checkpoint states.
-- Retired the standalone `idea-refine` skill immediately after extracting its useful shaping frameworks and evaluation criteria into `internal-gateway-idea-brainstorming` references, preserving its upstream license and removing the competing runtime entrypoint.
+- Retired the standalone `idea-refine` skill immediately after extracting its useful shaping frameworks and evaluation criteria into `internal-gateway-idea` references, preserving its upstream license and removing the competing runtime entrypoint.
 - Updated adjacent routing owners (`internal-agent-support-next-step`, `internal-agent-support-lane-change-engine`, `internal-gateway-simple-task`, `internal-gateway-critical-master`) to recognize the new gateway in handoffs and lane-change recommendations.
 - Updated `.github/agents/README.md`, `.github/README.md`, `INTERNAL_CONTRACT.md`, `docs`, wrapper-alignment, mode-contracts, subagent-patterns, home-sync catalog, token benchmarks, and regression tests for the four-gateway model.
 
@@ -133,7 +133,7 @@ Use this format for new updates:
 - Added `internal-python-runner.sh`, Bash wrappers for every executable repository Python entrypoint, explicit `PyYAML` requirements for `openai-skill-creator`, and wrapper-first invocation guidance across prompts, skills, scripts, security docs, and maintainer workflow references.
 - Hardened `.github/scripts/validate-copilot-customizations.py`, `tests/test_contract_runner.py`, and `tests/test_validate_copilot_customizations.py` so canonical operational agents must point only to real canonical escalation targets, must not self-route, and stale retired-agent references are caught case-insensitively.
 - Clarified `internal-router` and `internal-agent-routing-engine` so medium-confidence routing asks at most one targeted clarification question with two clear options before falling back to `internal-planning-leader`.
-- Strengthened `.github/skills/internal-code-review/SKILL.md` with a standalone quick-start so the skill stays usable directly as a tactical review asset, not only as the review guard's engine.
+- Strengthened `.github/skills/internal-review-code/SKILL.md` with a standalone quick-start so the skill stays usable directly as a tactical review asset, not only as the review guard's engine.
 - Refreshed `.github/README.md` so the maintainer-facing catalog now matches the live `internal-*`, `obra-*`, and imported support families, the canonical internal agent model, and the actual scripts and workflow present on disk after recent repository restructuring.
 
 ## 2026-04-04

.github/INVENTORY.md

@@ -32,6 +32,8 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 
 ## Skills
 
+- `.github/skills/addyosmani-code-review-and-quality/SKILL.md`
+- `.github/skills/addyosmani-code-simplification/SKILL.md`
 - `.github/skills/agent-os-discover-standards/SKILL.md`
 - `.github/skills/agent-os-index-standards/SKILL.md`
 - `.github/skills/agent-os-inject-standards/SKILL.md`
@@ -53,11 +55,11 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 - `.github/skills/awesome-copilot-codeql/SKILL.md`
 - `.github/skills/awesome-copilot-dependabot/SKILL.md`
 - `.github/skills/awesome-copilot-secret-scanning/SKILL.md`
+- `.github/skills/awesome-copilot-security-review/SKILL.md`
 - `.github/skills/grill-me/SKILL.md`
 - `.github/skills/internal-agent-creator/SKILL.md`
 - `.github/skills/internal-agent-support-lane-change-engine/SKILL.md`
 - `.github/skills/internal-agent-support-next-step/SKILL.md`
-- `.github/skills/internal-ai-resource-review/SKILL.md`
 - `.github/skills/internal-aws-governance/SKILL.md`
 - `.github/skills/internal-aws-lambda/SKILL.md`
 - `.github/skills/internal-aws-mcp-research/SKILL.md`
@@ -73,7 +75,6 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 - `.github/skills/internal-bash/SKILL.md`
 - `.github/skills/internal-changelog-automation/SKILL.md`
 - `.github/skills/internal-cloud-policy/SKILL.md`
-- `.github/skills/internal-code-review/SKILL.md`
 - `.github/skills/internal-context-handoff/SKILL.md`
 - `.github/skills/internal-copilot-audit/SKILL.md`
 - `.github/skills/internal-copilot-docs-research/SKILL.md`
@@ -84,7 +85,6 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 - `.github/skills/internal-excel/SKILL.md`
 - `.github/skills/internal-gateway-critical-master/SKILL.md`
 - `.github/skills/internal-gateway-execute-plans/SKILL.md`
-- `.github/skills/internal-gateway-idea-brainstorming/SKILL.md`
 - `.github/skills/internal-gateway-idea/SKILL.md`
 - `.github/skills/internal-gateway-simple-task/SKILL.md`
 - `.github/skills/internal-gateway-writing-plans/SKILL.md`
@@ -99,7 +99,6 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 - `.github/skills/internal-github-pr/SKILL.md`
 - `.github/skills/internal-github-strategic/SKILL.md`
 - `.github/skills/internal-go/SKILL.md`
-- `.github/skills/internal-high-level-review/SKILL.md`
 - `.github/skills/internal-java-project/SKILL.md`
 - `.github/skills/internal-java-spring-boot-development/SKILL.md`
 - `.github/skills/internal-java/SKILL.md`
@@ -116,6 +115,9 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 - `.github/skills/internal-python-project/SKILL.md`
 - `.github/skills/internal-python-script/SKILL.md`
 - `.github/skills/internal-python/SKILL.md`
+- `.github/skills/internal-review-ai-resources/SKILL.md`
+- `.github/skills/internal-review-code/SKILL.md`
+- `.github/skills/internal-review-high-level/SKILL.md`
 - `.github/skills/internal-skill-creator/SKILL.md`
 - `.github/skills/internal-tdd/SKILL.md`
 - `.github/skills/internal-terraform/SKILL.md`
@@ -124,7 +126,8 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 - `.github/skills/local-agent-sync-global-copilot-configs-into-repo/SKILL.md`
 - `.github/skills/local-agent-sync-install-ai-resources/SKILL.md`
 - `.github/skills/local-copilot-log-analyzer/SKILL.md`
-- `.github/skills/mattpocock-caveman/SKILL.md`
+- `.github/skills/mattpocock-handoff/SKILL.md`
+- `.github/skills/mattpocock-research/SKILL.md`
 - `.github/skills/openai-docx/SKILL.md`
 - `.github/skills/openai-gh-address-comments/SKILL.md`
 - `.github/skills/openai-gh-fix-ci/SKILL.md`
@@ -147,6 +150,7 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 - `.github/skills/superpowers-writing-plans/SKILL.md`
 - `.github/skills/terraform-terraform-search-import/SKILL.md`
 - `.github/skills/terraform-terraform-test/SKILL.md`
+- `.github/skills/vercel-find-skills/SKILL.md`
 
 ### Support-only imported office skills
 
@@ -168,21 +172,22 @@ These imported `openai-*` office skills remain support-only depth for repositori
 - `.github/scripts/lib/internal_skills.py`
 - `.github/scripts/lib/inventory.py`
 - `.github/scripts/lib/jsonc.py`
+- `.github/scripts/lib/repo_paths.py`
 - `.github/scripts/lib/shared.py`
+- `.github/scripts/lib/sync_exclusions.py`
 - `.github/scripts/lib/syncing.py`
 - `.github/scripts/lib/token_risks.py`
 - `.github/scripts/run.sh`
 - `.github/scripts/sync_copilot_catalog.py`
-- `.github/scripts/sync_home_ai_resources.py`
 - `.github/scripts/validate_internal_skills.py`
 
 ## Agents
 
-- `.github/agents/internal-code-review.agent.md`
 - `.github/agents/internal-gateway-critical-master.agent.md`
-- `.github/agents/internal-gateway-idea-brainstorming.agent.md`
+- `.github/agents/internal-gateway-idea.agent.md`
 - `.github/agents/internal-gateway-review.agent.md`
 - `.github/agents/internal-gateway-simple-task.agent.md`
+- `.github/agents/internal-review-code.agent.md`
 - `.github/agents/local-sync-external-resources.agent.md`
 - `.github/agents/local-sync-global-copilot-configs-into-repo.agent.md`
 - `.github/agents/local-sync-install-ai-resources.agent.md`

.github/README.md

@@ -10,10 +10,10 @@ customization assets maintained in `cloud-strategy.github`.
 ## Agents
 
 - Canonical repository-owned gateway agents:
-  `internal-gateway-idea-brainstorming`, `internal-gateway-review`,
+  `internal-gateway-idea`, `internal-gateway-review`,
   `internal-gateway-critical-master`, `internal-gateway-simple-task`
 - Specialist repository-owned review agents:
-  `internal-code-review` for code-focused review before merge or follow-up action.
+  `internal-review-code` for code-focused review before merge or follow-up action.
 - Approved `extended` retained plans execute through
   `internal-gateway-execute-plans`.
 - When extra provenance helps, offer it as an optional follow-up detail and accept

.github/agents/README.md

@@ -5,11 +5,11 @@ repo-only sync workflows.
 
 ## Agent-Owned Core
 
-- `internal-gateway-idea-brainstorming`: owns substantive idea definition,
+- `internal-gateway-idea`: owns substantive idea definition,
   critical challenge, and retained planning before execution.
 - `internal-gateway-review`: owns generic defect-first review for non-code and
   mixed artifacts before fixes.
-- `internal-code-review`: owns dedicated code-focused review for source, tests,
+- `internal-review-code`: owns dedicated code-focused review for source, tests,
   scripts, build metadata, dependency metadata, and code diffs.
 - `internal-gateway-critical-master`: owns pressure testing.
 - `internal-gateway-simple-task`: owns concrete execution and approved compact
@@ -19,9 +19,9 @@ repo-only sync workflows.
 
 | Agent | Use when |
 | --- | --- |
-| `internal-gateway-idea-brainstorming` | A vague idea or unresolved goal needs definition and retained planning. |
+| `internal-gateway-idea` | A vague idea or unresolved goal needs definition and retained planning. |
 | `internal-gateway-review` | A concrete non-code or mixed artifact needs defect-first review before fixes. |
-| `internal-code-review` | A concrete code target needs dedicated code review before merge or follow-up action. |
+| `internal-review-code` | A concrete code target needs dedicated code review before merge or follow-up action. |
 | `internal-gateway-critical-master` | A proposal or plan needs pressure before action. |
 | `internal-gateway-simple-task` | A concrete low-to-medium-risk task can finish through one focused lane. |
 

.github/agents/internal-gateway-idea-brainstorming.agent.md → .github/agents/internal-gateway-idea.agent.md

@@ -1,5 +1,5 @@
 ---
-name: internal-gateway-idea-brainstorming
+name: internal-gateway-idea
 description: "Use this agent when a repository-owned request starts with a vague idea, unclear goal, unresolved option set, or needs substantive definition, convergence, critical challenge, and retained planning before execution."
 tools: ["read", "edit", "search", "execute", "web"]
 disable-model-invocation: true
@@ -19,8 +19,8 @@ handoffs:
     send: false
 ---
 
-# Internal Gateway Idea Brainstorming
+# Internal Gateway Idea
 
 ## Core Skill
 
-- `internal-gateway-idea-brainstorming`
+- `internal-gateway-idea`

.github/agents/internal-gateway-review.agent.md

@@ -49,7 +49,7 @@ Evaluate the target through the dimensions that apply to its surface:
 - **Plans and review packages:** retained plans, specs, audit packages, issue analysis, and decision-support reports.
 - **Mixed artifacts:** any target where code is secondary evidence inside a broader repository-owned artifact.
 
-Prefer `internal-code-review` when the target is purely code: source, tests, scripts, build files, dependency files, generated-code boundaries, or a code-focused diff.
+Prefer `internal-review-code` when the target is purely code: source, tests, scripts, build files, dependency files, generated-code boundaries, or a code-focused diff.
 
 ## Critical Counter-Analysis
 
@@ -113,7 +113,7 @@ Use this report shape:
 
 - Use this agent when the user asks for review, audit, critique, merge-readiness assessment, prompt or agent review, workflow review, policy review, plan review, or artifact risk assessment.
 - Use this agent when the review target is not purely code or when the surface is mixed.
-- Prefer `internal-code-review` when the requested review is specifically for source code, tests, scripts, build files, dependency files, or a code-focused diff.
+- Prefer `internal-review-code` when the requested review is specifically for source code, tests, scripts, build files, dependency files, or a code-focused diff.
 - Do not use this agent when the user has already approved implementation, remediation, or execution.
 - Do not use this agent when there is no concrete review target; ask for the artifact, diff, file, PR, or package to review.
 - Do not delegate to peer agents or hand off to fix lanes. Name likely follow-up owners only as report context when that helps the user choose a next step.

.github/agents/internal-gateway-simple-task.agent.md

@@ -1,22 +1,9 @@
 ---
 name: internal-gateway-simple-task
-description: "Use this agent when a concrete low-to-medium-risk repository-owned task can be answered, edited, diagnosed, validated, or planned quickly, or switched to plan mode to produce a retained plan instead of same-chat execution."
+description: "Use this agent when a concrete low-to-medium-risk repository-owned task can be answered, edited, diagnosed, or validated quickly in one bounded run, and should stop with reason when complexity or cost breaks that boundary."
 tools: ["read", "edit", "search", "execute", "web"]
 disable-model-invocation: true
 agents: []
-handoffs:
-  - label: "Next step: Reopen planning"
-    agent: "internal-gateway-idea-brainstorming"
-    prompt: "Reopen planning because this task no longer fits the simple single-lane fast path. Preserve scope, validation, and risk, then choose the right retained-plan profile before execution."
-    send: false
-  - label: "Next step: Pressure-test task"
-    agent: "internal-gateway-critical-master"
-    prompt: "Pressure-test the reasoning, assumptions, or failure modes that made this task leave the simple fast path."
-    send: false
-  - label: "Next step: Review target"
-    agent: "internal-gateway-review"
-    prompt: "The work above became defect-first analysis rather than direct execution. Review the concrete target and stop before applying fixes."
-    send: false
 ---
 
 # Internal Gateway Simple Task

.github/agents/internal-code-review.agent.md → .github/agents/internal-review-code.agent.md

@@ -1,5 +1,5 @@
 ---
-name: internal-code-review
+name: internal-review-code
 description: "Senior repository code reviewer for source code, tests, scripts, build files, dependency files, and code-focused diffs before merge or follow-up action."
 tools: ["read", "search", "execute"]
 disable-model-invocation: true