synapse-hub 2.5.0 → 2.6.0

package/.agents/rules/skill-precedence.md

@@ -5,58 +5,38 @@ description: Skill Resolution Precedence, Inter-Skill Coordination, and Anti-Col
 
 # Skill Resolution Precedence & Anti-Collision Protocol
 
-> **Purpose:** Resolve overlapping trigger scopes between Project-Local Skills and External Plugins, as well as distinct operational boundaries among internal skills — eliminating context contagion, token bloat, and conflicting instructions.
+> **Purpose:** Resolve overlapping trigger scopes between Project-Local Skills and External Plugins, eliminating context contagion, token bloat, and conflicting instructions.
 
 ---
 
-## 1. Non-Negotiable Precedence Order
-
-When executing tasks within automated testing repositories, all AI Agents must strictly apply the following 3-tier hierarchy:
-
-```text
-[Tier 1: Project-Local Skills] (.agents/skills/*) 
-       v (Highest priority — Specialized, Context-Aware & Clean POM Enforced)
-[Tier 2: Core Project Rules] (.agents/rules/*)
-       v (Mandatory operating invariants & behavioral guardrails)
-[Tier 3: External Plugin Skills] (antigravity-testing-kit, chrome-devtools-plugin, generic plugins)
-       v (Suppressed whenever a Tier 1 skill exists)
-```
+## 1. Non-Negotiable 3-Tier Precedence Order
+`[Tier 1: Project-Local Skills] (.agents/skills/*)` > `[Tier 2: Core Rules] (.agents/rules/*)` > `[Tier 3: External Plugins] (generic plugins)`.
+Whenever a Tier 1 local skill exists, the external plugin skill is **strictly suppressed**.
 
 ---
 
-## 2. External Plugin Suppression Matrix (Tier 1 vs Tier 3)
-
-When an external plugin offers a capability that overlaps with a specialized Synapse Hub skill, the external skill is **strictly suppressed**:
-
-| Task Domain | REQUIRED Skill (Tier 1) | SUPPRESSED Skill (Tier 3) | Architectural Reason |
-|---|---|---|---|
-| **POM & Test Authoring** | `clean-pom-crafter`<br/>`lam-script-generator` | `QA Automation Engineer`, `Test Generator` | Generic plugins generate raw XPaths and Selenium boilerplate; Hub strictly enforces Flat Architecture and zero raw locators in scripts. |
-| **Code Change Review** | `senior-code-review` | `Generic PR Reviewer`, `Code Reviewer` | Evaluates 6 pillars (Bugs, Security, Concurrency, Missing Tests, Speed, Bloat) specifically against Git Diff. |
-| **Locator Healing & Diffing** | `self-healing-locator`<br/>`failure-autopsy-and-healing` | `Locator Healer Agent` | Uses token-efficient semantic AOM diffing (Role > Label > TestId) instead of dumping thousands of raw HTML lines. |
-| **Flaky Test Triage & RCA** | `failure-autopsy-and-healing`<br/>`flaky-test-sentinel-and-quarantine` | `Flaky Test Analyzer` | Triage occurs via 0-token JUnit XML parsing, screenshot autopsy, and SQLite episodic memory cache (`global_cache.db`). |
-| **Live Probing & Inspection** | `playwright-live-interaction` | `Smart Locator Agent` | Direct CDP network idle 0, dynamic overlay detachment, and in-browser helper integration under 200ms. |
-| **Accessibility (WCAG)** | `wcag-audit-patterns` *(Guideline)* | `a11y-debugging` *(Tooling Only)* | `wcag-audit-patterns` enforces WCAG 2.2 A/AA criteria; Chrome DevTools MCP is used strictly for low-level node inspection. |
+## 2. External Plugin Suppression Rules (Tier 1 overrides Tier 3)
+- **POM & Test Authoring:** Use `clean-pom-crafter` / `lam-script-generator`. Suppress generic QA/test plugins. Flat Clean POM only; no raw XPaths in test scripts.
+- **Code Review:** Use `senior-code-review` (6 pillars against git diff). Suppress generic PR reviewers.
+- **Locator Healing:** Use `self-healing-locator` / `failure-autopsy-and-healing` (AOM diffing). Suppress generic locator healers.
+- **Flaky Test Triage:** Use `flaky-test-sentinel-and-quarantine` (episodic SQLite memory + JUnit parsing).
+- **Live Probing:** Use `playwright-live-interaction` (CDP idle 0 under 200ms). Suppress generic smart locators.
+- **Accessibility:** Use `wcag-audit-patterns` for WCAG 2.2 A/AA criteria; use Chrome DevTools MCP strictly for low-level node inspection.
 
 ---
 
-## 3. Internal Inter-Skill Coordination & Boundary Separation
-
-To prevent decision paralysis among internal skills in `.agents/skills/`, agents must strictly adhere to the following boundary matrix:
-
-| Functional Area | Primary Skill | Sibling Skill | Distinct Responsibility & Hand-Off |
-|---|---|---|---|
-| **Code Creation** | `lean-code-ladder` | `surgical-coding-principles` | • `lean-code-ladder` governs **what to build** (descends 7-rung ladder, selects smallest working solution).<br/>• `surgical-coding-principles` governs **where to touch** (keeps git diff surgical, no unrelated file edits). |
-| **Technical Debt** | `technical-debt-harvester` | `code-refactoring-refactor-clean` | • `technical-debt-harvester` is the **accountant** (scans and tracks `shortcut:` comments in Markdown ledgers).<br/>• `code-refactoring-refactor-clean` is the **surgeon** (executes SOLID refactoring and code smell remediation). |
-| **Quality Review** | `senior-code-review` | `review-spec` (`goldfish_review`) | • `senior-code-review` audits **Source Code Diffs** (uncommitted / staged git changes).<br/>• `review-spec` audits **Requirements & User Stories** in a 0-context stress-test (Elephant-Goldfish model). |
-| **System Audit** | `repo-quality-audit` | `analyze_project` (`tools/`) | • `analyze_project.py` produces **deterministic facts** (AST map, env check, data flow, 9 gates DoD).<br/>• `repo-quality-audit` applies **senior engineering judgment** (evaluates real load, ranks *"Fix #1 first"*). |
-| **API Testing** | `api-spec-to-e2e-matrix` | `api-network-mocking-interception` | • `api-spec-to-e2e-matrix` compiles **test matrices** from OpenAPI specs.<br/>• `api-network-mocking-interception` stubs routes and injects **chaos network faults** during UI/API test runs. |
-| **Failure Analysis** | `self-healing-locator` | `failure-autopsy-and-healing` | • `self-healing-locator` fixes **individual broken Page Class selectors**.<br/>• `failure-autopsy-and-healing` triages **suite-wide run crashes**, JUnit XML reports, and logs. |
-| **DoD Verification** | `verification-before-completion` | `antigravity-test-sentinel` | • `verification-before-completion` enforces the **evidence protocol** (fresh command output required in session).<br/>• `antigravity-test-sentinel` is the **hard gatekeeper** (blocks task completion until all 9 Quality Gates pass). |
+## 3. Internal Inter-Skill Coordination & Boundaries
+- **Code Authoring:** `lean-code-ladder` decides *what* to build (7-rung ladder); `surgical-coding-principles` restricts *where* to touch (surgical git diff).
+- **Technical Debt:** `technical-debt-harvester` tracks `shortcut:` markers; `code-refactoring-refactor-clean` executes refactoring.
+- **Quality Review:** `senior-code-review` audits source diffs; `review-spec` audits requirements/stories (0-context stress test).
+- **System Audit:** `tools/analyze_project.py` gathers facts (AST, env, gates); `repo-quality-audit` prioritizes "Fix #1 first".
+- **API Testing:** `api-spec-to-e2e-matrix` compiles test matrices; `api-network-mocking-interception` stubs routes and chaos faults.
+- **Failure Analysis:** `self-healing-locator` heals individual locators; `failure-autopsy-and-healing` triages suite-wide crashes.
+- **DoD Gatekeeper:** `verification-before-completion` checks fresh command evidence; `antigravity-test-sentinel` enforces all 10 gates.
 
 ---
 
 ## 4. Strict Prohibitions
-
-1. **Zero Generic Test Boilerplate:** Never generate legacy Selenium, Cucumber, or Object Repository (`findTestObject`) code from external plugins.
-2. **Zero Raw HTML Dumps:** Never dump full HTML trees into context for locator healing; always extract compact AOM subtrees (< 500 tokens).
-3. **Zero Unverified Assertions:** Never complete a code or test task without executing fresh verification via `tools/verify_all.py`.
+1. **Zero Generic Boilerplate:** Never generate legacy Selenium, Cucumber, or `findTestObject` code.
+2. **Zero Raw HTML Dumps:** Extract compact AOM subtrees (< 500 tokens); never dump raw HTML trees.
+3. **Zero Unverified Assertions:** Never complete tasks without running fresh verification via `tools/verify_all.py`.

package/.agents/rules/systematic-debugging.md

@@ -31,7 +31,7 @@ This rule governs all AI Agents operating on the repository. It mandates strict
      ```bash
      python3 tools/verify_all.py
      ```
-   - All 9 Gates must return `PASS`. If any gate fails, the task is NOT complete.
+   - All 10 Gates must return `PASS`. If any gate fails, the task is NOT complete.
 2. **Targeted Re-Test:**
    - After modifying Page Classes, check impacted Test Cases with:
      ```bash
@@ -46,34 +46,15 @@ This rule governs all AI Agents operating on the repository. It mandates strict
 
 ## 3. Situational Tool Dispatch Matrix & Zero-Command Autonomy
 
-> 🚀 **Zero-Command Autonomous Invariant (Zero Manual Commands):**  
-> The user **NEVER** needs to remember syntax or manually type tool commands (`agent-qa setup`, `agent-qa analyze`, `verify_all.py`...).  
-> The AI Agent **MUST AUTONOMOUSLY recognize context and trigger** the corresponding tools below on-demand whenever the situation arises.  
->  
-> 🎯 **On-Demand Activation Principle (Situation-Specific — Never Run Blindly):**  
-> Tools assigned to AI and Subagents are **situational weapons**, **NEVER executed all at once**. Agents draw the specific tool from the arsenal if and only if a concrete need arises (e.g.: failing test triggers `auto_heal`, new project triggers `setup_project`, API breaking change triggers `api_drift_sentinel`).
-
-| Context / Trigger | Mandatory Tool | Specific Objective |
-| :--- | :--- | :--- |
-| **New project / Missing `PROJECT_AI_GUIDE.md` / Fresh clone** | `python3 tools/setup_project.py [target]` | 100% Autonomous: Detects framework (Playwright/Katalon/Pytest), generates `PROJECT_AI_GUIDE.md`, installs `pre-push` hook, extracts `repo_map.txt`, runs initial audit. |
-| **User requests: "analyze project" / "re-analyze" / "project audit"** | `python3 tools/analyze_project.py [target]` | Execute comprehensive 5-in-1 health audit, sync repo_map, infer_linter, data_flow, verify_all & generate PROJECT_HEALTH_REPORT.md.<br/>**Post-Action:** Stage, commit & push updated project files (`PROJECT_HEALTH_REPORT.md`, `repo_map.txt`) to git. |
-| **User requests: "review code" / "review diff" / "senior review"** | `python3 tools/senior_code_review.py` | 6-pillar code change review (Bugs, Security, Concurrency, Missing Tests, Speed, Bloat). |
-| **User requests: "scan debt" / "list shortcuts" / "harvest debt"** | `python3 tools/debt_harvester.py` | Harvest `shortcut:` technical debt markers across repo into tracked markdown ledger. |
-| **Starting task / Querying Page Class methods** | `tools/repo_map.txt`<br/>*(run `python3 tools/repo_map.py` if classes changed)* | Read compressed 500-token map for signatures; avoid reading 4,000-line files. |
-| **Dispatching Browser Actions (Live/CDP)** | `python3 tools/safety_firewall.py --dry-run` | Mandatory Pre-execution Hook: Block irreversible/destructive operations before browser dispatch. |
-| **Creating or updating Test Scripts** | `python3 tools/infer_linter.py` | Run AST scan for Fake-Pass (0 asserts) and empty catch blocks. |
-| **New/Modified Test Case Quality** | `python3 tools/micro_mutator.py --min-score 80` | AST Mutation Testing: Reject test suites with mutation score < 80%. |
-| **Before Git Commit or Completing Task** | `python3 tools/verify_all.py` | Validate all 9 Quality Gates DoD. |
-| **After modifying Page Classes** | `python3 tools/test_impact.py --git-diff` | Scope impacted test cases; avoid re-running entire test suites. |
-| **When Test FAILS in CLI/KRE** | `python3 tools/pinpoint_failure.py` | Parse JUnit XML to identify exact failing line and exception in 0.1s. |
-| **When CLI / Gradle logs are verbose** | `python3 tools/distill_log.py <log>` | Filter 95% noise; preserve only actionable stacktraces and pointers. |
-| **Handling UI exceptions (Overlay, Stale)** | `python3 tools/cache_resolver.py query "<error>"` | Lookup 0-token solution from local SQLite memory cache before improvising. |
-| **Pre-Push / Suite Acceptance** | `python3 tools/trace_data_flow.py` | Run Taint Analysis to verify no orphan database junk remains uncleaned. |
-| **Canary Self-Healing Audit** | `python3 tools/agent_canary.py --run` | Inject 8 failure vectors to benchmark MTTR and autonomous recovery rate. |
-| **Testing GIS Canvas / Chart without DOM** | `python3 tools/visual_diff_canvas.py` | Compare pixel / SSIM to detect visual rendering regression. |
-| **Pulling code / New clone** | `python3 tools/cache_resolver.py init` | Automatically sync Central Agent Memory (`~/.agent_memory/global_cache.db`). |
-| **Before authoring test for Page/Flow** | `python3 tools/cache_resolver.py get-lessons --context "<page>"` | Query top 2 episodic lessons learned to avoid repeating past failure patterns. |
-| **After healing a bug / failure** | `python3 tools/cache_resolver.py record-lesson` | Record a concise 2-line lesson into SQLite memory for cross-session reflexion. |
+> 🚀 **Zero-Command Autonomous Invariant:** The user **NEVER** needs to manually type tool commands. The AI Agent **MUST AUTONOMOUSLY recognize context and trigger** the corresponding tools on-demand. Never run tools blindly; invoke only when the concrete situation arises.
+
+- **Setup & Audit:** New project -> `tools/setup_project.py`; Project audit -> `tools/analyze_project.py`; Code review -> `tools/senior_code_review.py`; Debt scan -> `tools/debt_harvester.py`.
+- **Quality Gates & DoD:** Pre-commit/Handoff -> `tools/verify_all.py` (10 Gates DoD); Script lint -> `tools/infer_linter.py`; Mutation testing -> `tools/micro_mutator.py --min-score 80`.
+- **Failure Autopsy & Healing:** Test failure -> `tools/pinpoint_failure.py` (parse JUnit XML in 0.1s); Iterative repair -> `tools/auto_heal_reflexion.py`; Reversible rollback -> `tools/reversible_sandbox.py`.
+- **Context & Safety:** Verbose logs -> `tools/distill_log.py`; Destructive browser actions -> `tools/safety_firewall.py`; Method signatures -> `tools/repo_map.txt`.
+- **Memory & Reflexion:** UI exceptions -> `tools/cache_resolver.py query "<error>"`; Query/Save proven patterns -> `tools/skill_vault.py`.
+
+*(For the complete CLI parameters and full tools catalog, refer to [tools/TOOLS_RUNBOOK.md](file://tools/TOOLS_RUNBOOK.md)).*
 
 ---
 

package/.agents/skills/token-and-context-optimizer/references/context_engineering_guide.md

@@ -0,0 +1,49 @@
+# Context Engineering & Token Optimization Guide (Full Architecture)
+
+*(Synthesized from `muratcankoylan/Agent-Skills-for-Context-Engineering`, `alexgreensh/token-optimizer`, and `obra/superpowers`)*
+
+---
+
+## 1. Pillar 1: Observation Masking
+Raw tool outputs (CLI execution logs, Gradle builds, browser console traces) contain 90% repetitive noise and low-signal tokens.
+- **Log Truncation & Summarization:** Never dump thousands of lines into the active conversation. Extract only: failing line number, exception name, test case identifier (`TC-xxx`), and status.
+- **Pointer Masking:** Use structured references pointing to files on disk: `[Full raw log saved to file://<path>; 2,400 verbose lines omitted]`.
+
+---
+
+## 2. Pillar 2: Progressive Disclosure
+Never load large codebases or giant classes (over 500 lines) into context at once. Load information in 3 progressive tiers:
+- **Tier 1:** High-Level Index & Repo Map (< 150 lines) via `tools/repo_map.txt`.
+- **Tier 2:** Graph Semantic Scoping via `graphify explain` or `test_impact.py`.
+- **Tier 3:** Targeted Micro-Read (20-50 lines using `StartLine`/`EndLine`).
+
+---
+
+## 3. Pillar 3: KV-Cache Friendly Ordering
+LLM inference engines cache Key-Value (KV) attention states for identical prompt prefixes.
+- **Static Prefix First:** Keep instructions, rules, and tool schemas immutable at the top.
+- **Append-Only Dynamic State:** Only append new test results and tool observations at the bottom.
+- **Predictable Format:** Use identical pre-flight status badges on every turn to maximize cache hits (> 85%).
+
+---
+
+## 4. Pillar 4: Scoped Context & Compaction Anchoring
+- **Compaction State Anchoring:** Critical state must be persisted to disk in `PROJECT_STATE.md`. When compaction fires, re-anchor immediately from disk with zero memory loss.
+- **Workspace Isolation (`Workspace: 'share'`):** Subagents use isolated worktrees to prevent dirty tree collisions.
+- **Zero Context Contagion:** Subagents return distilled 3-5 line summaries; stdout remains in subagent sandbox.
+- **Data Partitioning:** Subagents append agent IDs to test data (`uniqueCode = "AUTO_" + time + "_SUB" + id`).
+
+---
+
+## 5. Pillar 5: Semantic Context Distillation (Pure Signal, Zero Noise)
+All sensory inputs must pass through deterministic filters:
+- **CLI Logs (`tools/distill_log.py`):** Truncate 95% of verbose lines.
+- **DOM Purifier (`qa.getCompactAOM`):** Strictly forbidden to send raw HTML. Use compact AOM (< 500 tokens).
+- **Universal IR (`tools/universal_ir.py`):** Author clean universal IR before emitting framework-specific code.
+
+---
+
+## 6. Pillar 6: Elephant-Goldfish Memory Model
+- **The Elephant (Stateful Orchestrator):** Narrows problem boundaries, gathers intent, drafts specs in `docs/specs/*.md`, maintains `PROJECT_STATE.md`. Never writes tests during design phase.
+- **The Goldfish (Stateless Subagent Swarm):** Fresh subagent with ZERO conversation history; evaluates solely cold artifacts on disk via `tools/goldfish_review.py`.
+- **Air-Gap Data Contract:** All inter-stage data exchanges pass via disk files (JSON/JUnit XML), never raw prompt inheritance.

package/AGENTS.md

@@ -61,7 +61,12 @@ You are a lazy senior developer. The best code is the code never written. Solve
    - User asks to scan debt / shortcuts -> Autonomously run `tools/debt_harvester.py`.
    - Test failure occurs in runner -> Autonomously run `tools/pinpoint_failure.py` / `tools/auto_heal.py`.
    - Verifying test assertion quality -> Autonomously run `tools/micro_mutator.py` (reject if Mutation Score < 80%).
-   - Before completing code tasks -> Autonomously run `tools/verify_all.py` (9 Quality Gates DoD).
+   - Complex test failures / iterative self-healing -> Run `tools/auto_heal_reflexion.py` (Noah Shinn Reflexion K=3).
+   - Reversible sandbox mutations / rollback -> Run `tools/reversible_sandbox.py`.
+   - Querying / Storing verified PageClass library -> Run `tools/skill_vault.py`.
+   - Vague requirements / story ambiguity -> Autonomously run `tools/interview_story.py`.
+   - Optimizing assertions against surviving mutants -> Run `tools/textgrad_mutation_optimizer.py`.
+   - Before completing code tasks -> Autonomously run `tools/verify_all.py` (10 Quality Gates DoD).
 
 ---
 

package/NOTICE

@@ -107,10 +107,19 @@ Third-Party Borrowings (idea- and text-level)
     modified.
 
 17. ponytail (https://github.com/DietrichGebert/ponytail) - MIT License,
-    Copyright (c) 2026 DietrichGebert. The 7-rung reuse-first ladder, the
-    completeness rules, and the never-cut floor in
-    .agents/skills/lean-code-ladder/SKILL.md are adapted from the ponytail
-    lazy-senior model; wording, structure, and examples modified.
+    Copyright (c) 2026 DietrichGebert. Core patterns and concepts adapted
+    from the Ponytail v5.3 lazy-senior model include:
+    - The 7-rung reuse-first ladder and never-cut floor in
+      .agents/skills/lean-code-ladder/SKILL.md
+    - 6-pillar code change review in .agents/skills/senior-code-review/SKILL.md
+      and tools/senior_code_review.py
+    - Codebase quality audit in .agents/skills/repo-quality-audit/SKILL.md
+    - Shortcut technical debt harvesting in
+      .agents/skills/technical-debt-harvester/SKILL.md and tools/debt_harvester.py
+    - Benchmark gain reporting in .agents/skills/lean-impact-scoreboard/SKILL.md
+    - Claude Code slash commands in commands/ (synapse-* and ponytail-* aliases)
+    All components were re-engineered, adapted, and integrated for enterprise
+    test automation and Clean POM architecture.
 
 18. planning-with-files (https://github.com/OthmanAdi/planning-with-files)
     - MIT License, Copyright (c) 2026 Ahmad Adi. The 3-file planning pattern
@@ -178,3 +187,30 @@ Third-Party Borrowings (idea- and text-level)
     and token throughput optimization in
     .agents/skills/agent-orchestration-multi-agent-optimize/SKILL.md are
     synthesized from autonomous multi-agent design patterns (crewAI, AutoGen).
+
+29. Context Engineering & Token Optimization (muratcankoylan & alexgreensh)
+    - MIT License. Observation masking, progressive disclosure, KV-cache
+    ordering, and token budget management in .agents/rules/context-engineering.md
+    and .agents/skills/token-and-context-optimizer/SKILL.md are adapted from
+    muratcankoylan/Agent-Skills-for-Context-Engineering and alexgreensh/token-optimizer.
+
+30. vercel-labs/agent-browser (https://github.com/vercel-labs/agent-browser)
+    - MIT License. Compact accessibility tree snapshots and semantic node
+    filtering referenced in .agents/skills/playwright-live-interaction/references/
+    compact_accessibility_snapshots.md are adapted from vercel-labs/agent-browser.
+
+31. fugazi/test-automation-skills-agents (https://github.com/fugazi/test-automation-skills-agents)
+    - MIT License. The closed-loop failure triage and investigation steps in
+    .agents/skills/failure-autopsy-and-healing/references/qa_investigation_protocol.md
+    are adapted from fugazi/test-automation-skills-agents.
+
+32. LaVague AI Large Action Model (https://github.com/lavague-ai/LaVague)
+    - Apache License 2.0. The concept of translating natural language User
+    Stories and acceptance criteria into deterministic web actions in
+    .agents/skills/lam-script-generator/SKILL.md is inspired by the LaVague
+    Large Action Model (LAM) framework.
+
+33. Graphify (https://github.com/Graphify-Labs/graphify)
+    - Apache License 2.0. Knowledge graph generation and AST dependency blast
+    radius mapping in .agents/rules/graphify.md and
+    .agents/skills/graphify-impact-analyzer/SKILL.md are adapted from Graphify.

package/README.en.md

@@ -4,9 +4,9 @@
 [🇻🇳 Tiếng Việt](README.md) | [🇬🇧 English Edition](README.en.md)
 
 > **Core Mission:** A standalone, zero-dependency Linter & Guardrail engine (zero external dependencies for core engine & DoD gates) protecting test suite integrity in the era of AI code generation — Catching tautological "fake-pass" tests, eliminating hard sleeps, distilling 95% CI log noise, and enforcing Clean POM architecture. Specialized tools (Excel export, Canvas visual diff) leverage standard optional extras (`openpyxl`, `Pillow`).  
-> **Extended Ecosystem:** Bundled with 42 production QA skills, 6 specialized AI roles, and 9 DoD Quality Gates supporting Playwright, Cypress, Pytest, and Katalon.  
+> **Extended Ecosystem:** Bundled with 42 production QA skills, 6 specialized AI roles, and 10 DoD Quality Gates supporting Playwright, Cypress, Pytest, and Katalon.  
 > **Author:** Thế Vị ([@TeeVee998](https://github.com/TeeVee998))  
-> **Hub Version:** `v2.5.0` | **Scope:** 42 Standardized Skills, 6 Specialized AI Agents, 60 CLI Commands & 60+ Test Engineering Tools, 9 DoD Quality Gates.
+> **Hub Version:** `v2.6.0` | **Scope:** 42 Standardized Skills, 6 Specialized AI Agents, 68 CLI Commands & 68+ Test Engineering Tools, 10 DoD Quality Gates.
 
 [![npm version](https://img.shields.io/npm/v/synapse-hub.svg?style=flat-square&color=blue)](https://www.npmjs.com/package/synapse-hub)
 [![node version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg?style=flat-square)](https://nodejs.org)
@@ -110,7 +110,7 @@ npx synapse-hub uninstall
 
 ### Run Quality DoD Gates:
 ```bash
-npx synapse-hub verify         # Execute 9 Quality Gates DoD (Gate 0–8)
+npx synapse-hub verify         # Execute 10 Quality Gates DoD (Gate 0–9)
 npx synapse-hub analyze        # Comprehensive 5-in-1 project health audit
 ```
 
@@ -152,6 +152,7 @@ repos:
 | **Gate 6** | **Credential Security** | Blocks hardcoded plaintext passwords, private keys, and secret tokens in code. |
 | **Gate 7** | **Static Defect & Fake-Pass Sentinel** | Static heuristic analysis catching 0-assertion tests, empty catch blocks, hardcoded/variable sleeps (≥ 3000ms), and unawaited promises. |
 | **Gate 8** | **Assertion Sensitivity Sentinel** | Injects syntactic micro-mutations linked via dataflow (Ultra-fast Heuristic Static mode ~0.1s; pass `--test-cmd` for runtime re-test; requires Score ≥ 80%). |
+| **Gate 9** | **Tier-2 Skill Routing & Collision Guard** | Audits semantic descriptions and activation triggers between skills; prevents ambiguous overlap collisions (Threshold < 0.75). |
 
 ---
 
@@ -161,7 +162,7 @@ repos:
 | :--- | :--- | :--- |
 | **Fresher / Junior** | Learn fast, deliver immediately, understand weak asserts | • `npx synapse-hub export-excel`: Generate standard test cases.<br/>• `npx synapse-hub lint ./tests`: Understand why assertions are tautological.<br/>• Inspect Clean POM examples in `examples/practices/`. |
 | **Mid-Level** | Reduce flakiness, cut locator maintenance | • `npx synapse-hub flaky scan ./tests`: Detect flaky tests and quarantine them.<br/>• `npx synapse-hub heal`: Semantic locator healing via AOM diffing.<br/>• Add linter to pre-commit git hooks. |
-| **Senior / Lead** | Control, measurement, CI/CD safety gates | • `npx synapse-hub verify`: 9 Automated DoD Gates in CI.<br/>• `npx synapse-hub mutate ./tests`: Heuristic assertion sensitivity analysis before merge.<br/>• Standard Markdown/JSON telemetry for PR review bots. |
+| **Senior / Lead** | Control, measurement, CI/CD safety gates | • `npx synapse-hub verify`: 10 Automated DoD Gates in CI.<br/>• `npx synapse-hub mutate ./tests`: Heuristic assertion sensitivity analysis before merge.<br/>• Standard Markdown/JSON telemetry for PR review bots. |
 
 > *Pro Tip: If installed globally (`npm i -g synapse-hub`), you can use the shorter syntax `synapse-hub <cmd>` or equivalent aliases `synapse`, `agent-qa`.*
 
@@ -250,7 +251,7 @@ To uphold our strict **Truth Anchor** standard, we openly disclose known system
 | 1 | `clean-pom-crafter` | Clean POM & Flat Architecture page class design (zero raw selectors in test scripts). |
 | 2 | `playwright-live-interaction` | Live DOM/AOM exploration and < 200ms selector verification via headless Playwright. |
 | 3 | `failure-autopsy-and-healing` | Failure triage from JUnit XML/screenshots and automated broken locator repair. |
-| 4 | `infer_linter` / `antigravity-test-sentinel` | Quality gatekeeper enforcing zero fake-passes and 9 DoD quality gates. |
+| 4 | `infer_linter` / `antigravity-test-sentinel` | Quality gatekeeper enforcing zero fake-passes and 10 DoD quality gates. |
 | 5 | `token-and-context-optimizer` | Prompt context optimization, log distillation, and Context Rot prevention. |
 | 6 | `flaky-test-sentinel-and-quarantine` | Non-deterministic test detection, flakiness scoring, and quarantine management. |
 | 7 | `api-spec-to-e2e-matrix` | Convert OpenAPI/Swagger specifications into E2E testing matrices. |
@@ -290,7 +291,7 @@ To uphold our strict **Truth Anchor** standard, we openly disclose known system
 | 41 | `technical-debt-harvester` | Harvests `shortcut:` comments into an actionable debt ledger via `agent-qa debt`. |
 | 42 | `lean-impact-scoreboard` | Displays empirical benchmark scoreboard of code reduction %, token savings, and execution speed. |
 
-> **Open source & credits:** Skills 31-42 are adapted from open-source projects (andrej-karpathy-skills, ponytail, planning-with-files, anthropics/skills, superpowers, wshobson/agents) — full license and author details in `NOTICE` (entries 16-21); companion external-tool guide in `docs/adopted-ecosystem-tools.md`.
+> **Open source & credits:** Skills and tools are adapted and specialized from open-source projects (NVIDIA SkillSpector, andrej-karpathy-skills, ponytail, planning-with-files, anthropics/skills, superpowers, wshobson/agents, vercel-labs/agent-browser, LaVague, graphify...) — full license and author attribution details in `NOTICE` (entries 1-33); companion external-tool guide in `docs/adopted-ecosystem-tools.md`.
 
 </details>
 
@@ -298,13 +299,13 @@ To uphold our strict **Truth Anchor** standard, we openly disclose known system
 
 ## 🛠️ 8. CLI Tooling Arsenal (tools/)
 
-Synapse Hub includes over 60 utility tools implemented entirely in the **Python Standard Library** (zero external dependencies):
+Synapse Hub includes over 68 utility tools implemented entirely in the **Python Standard Library** (zero external dependencies):
 
 ```bash
 # 1. Diagnose local environment (Node, Python, Chrome, Git)
 npx synapse-hub doctor
 
-# 2. Run 9 Quality Gates DoD Verification
+# 2. Run 10 Quality Gates DoD Verification (Gate 0–9)
 npx synapse-hub verify
 
 # 3. Scan for fake-passes, tautologies, and empty catch blocks
@@ -321,6 +322,21 @@ npx synapse-hub mutate ./tests
 
 # 7. Detect and quarantine flaky tests
 npx synapse-hub flaky scan ./tests
+
+# 8. Query lifelong verified PageClass library (Voyager SkillVault)
+python tools/skill_vault.py --query "table_pagination"
+
+# 9. Episodic reflection self-healing loop (Noah Shinn Reflexion K=3)
+python tools/auto_heal_reflexion.py --test "TC_Checkout_01" --error "ElementClickInterceptedException"
+
+# 10. Interrogate ambiguous requirements (Pocock Grilling Engine)
+python tools/interview_story.py "As a user I want to checkout"
+
+# 11. Optimize assertion prompts against mutants (TextGrad Loss Optimizer)
+python tools/textgrad_mutation_optimizer.py --file tests/test_login.py
+
+# 12. Benchmark agent tool-calling precision (Gorilla BFCL Benchmark)
+python tools/synapse_qa_bench.py
 ```
 
 *(See [docs/CLI_REFERENCE.md](docs/CLI_REFERENCE.md) and [tools/TOOLS_RUNBOOK.md](tools/TOOLS_RUNBOOK.md) for parameter details).*

package/README.md

@@ -4,9 +4,9 @@
 [🇻🇳 Tiếng Việt](README.md) | [🇬🇧 English Edition](README.en.md)
 
 > **Định vị cốt lõi:** Bộ Linter & Guardrails độc lập (zero external dependencies cho core engine & DoD gates) bảo vệ độ tin cậy của test suite khi AI viết code — Phát hiện & ngăn chặn test "pass ảo" (0 assert, tautology), loại bỏ hoàn toàn sleep cố định, nén 95% log CI/CD, và chuẩn hóa cấu trúc Clean POM. Các tính năng nâng cao (xuất bảng Excel chuẩn doanh nghiệp, so sánh ảnh Canvas) sử dụng thư viện mở rộng tùy chọn (`openpyxl`, `Pillow`).  
-> **Module mở rộng:** Sẵn sàng kết nối 42 kỹ năng QA chuyên sâu, 6 vai trò AI Swarm và 9 Cổng kiểm định DoD hỗ trợ Playwright, Cypress, Pytest và Katalon.  
+> **Module mở rộng:** Sẵn sàng kết nối 42 kỹ năng QA chuyên sâu, 6 vai trò AI Swarm và 10 Cổng kiểm định DoD hỗ trợ Playwright, Cypress, Pytest và Katalon.  
 > **Tác giả:** Thế Vị ([@TeeVee998](https://github.com/TeeVee998))  
-> **Phiên bản Hub:** `v2.5.0` | **Quy mô:** 42 Kỹ năng chuẩn hóa, 6 Vai trò AI Agent, 60 Lệnh CLI & 60+ Công cụ kiểm thử chuyên sâu, 9 Cổng kiểm định DoD.
+> **Phiên bản Hub:** `v2.6.0` | **Quy mô:** 42 Kỹ năng chuẩn hóa, 6 Vai trò AI Agent, 68 Lệnh CLI & 68+ Công cụ kiểm thử chuyên sâu, 10 Cổng kiểm định DoD.
 
 [![npm version](https://img.shields.io/npm/v/synapse-hub.svg?style=flat-square&color=blue)](https://www.npmjs.com/package/synapse-hub)
 [![node version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg?style=flat-square)](https://nodejs.org)
@@ -108,9 +108,9 @@ npx synapse-hub setup
 npx synapse-hub uninstall
 ```
 
-### Chạy kiểm định 9 Cổng Chất Lượng (DoD Gates):
+### Chạy kiểm định 10 Cổng Chất Lượng (DoD Gates):
 ```bash
-npx synapse-hub verify         # Kiểm tra 9 Cổng Chất Lượng DoD (Gate 0–8)
+npx synapse-hub verify         # Kiểm tra 10 Cổng Chất Lượng DoD (Gate 0–9)
 npx synapse-hub analyze        # Báo cáo sức khỏe dự án (PROJECT_HEALTH_REPORT.md)
 ```
 
@@ -152,6 +152,7 @@ repos:
 | **Gate 6** | **Bảo Vệ Bí Mật & Mật Khẩu** | Quét chặn plaintext password, private keys hoặc API token lưu cứng trong code. |
 | **Gate 7** | **Quét Lỗi Tĩnh & Bắt Test Pass Ảo** | Tự động phát hiện test 0 assertion, try-catch bỏ qua ngoại lệ ngầm, sleep cố định (≥ 3000ms) và unawaited expect. |
 | **Gate 8** | **Đo Độ Nhạy Assert (Micro-Mutation)** | Đảm bảo các câu lệnh assert bắt được lỗi thật khi code bị biến đổi (Chế độ Heuristic Static ~0.1s; truyền `--test-cmd` cho runtime re-test; yêu cầu điểm ≥ 80%). |
+| **Gate 9** | **Điều Phối Kỹ Năng & Ngăn Xung Đột (Skill Collision Guard)** | Kiểm tra độ tương đồng ngữ nghĩa và trigger activation giữa các skill; chặn xung đột trùng lặp (Threshold < 0.75). |
 
 ---
 
@@ -161,7 +162,7 @@ repos:
 | :--- | :--- | :--- |
 | **Fresher / Junior** | Học nhanh, ra việc ngay, hiểu vì sao test yếu | • `npx synapse-hub export-excel`: Tạo test case chuẩn chỉnh.<br/>• `npx synapse-hub lint ./tests`: Giải thích vì sao assert yếu hoặc pass ảo.<br/>• Tham khảo mẫu Clean POM chuẩn trong `examples/practices/`. |
 | **Mid-Level** | Bớt flaky, giảm chi phí bảo trì locator | • `npx synapse-hub flaky scan ./tests`: Dò tìm test chập chờn và phân nhóm cách ly.<br/>• `npx synapse-hub heal`: Gợi ý thay thế locator hỏng qua phân tích cây AOM.<br/>• Tích hợp linter vào pre-commit hook. |
-| **Senior / Lead** | Đo lường, kiểm soát chất lượng, an toàn CI/CD | • `npx synapse-hub verify`: 9 Cổng chất lượng DoD tự động trong CI.<br/>• `npx synapse-hub mutate ./tests`: Kiểm tra độ nhạy của assertion trước khi merge PR.<br/>• Báo cáo chuẩn Markdown/JSON dễ dàng gắn vào GitHub Actions/GitLab CI. |
+| **Senior / Lead** | Đo lường, kiểm soát chất lượng, an toàn CI/CD | • `npx synapse-hub verify`: 10 Cổng chất lượng DoD tự động trong CI.<br/>• `npx synapse-hub mutate ./tests`: Kiểm tra độ nhạy của assertion trước khi merge PR.<br/>• Báo cáo chuẩn Markdown/JSON dễ dàng gắn vào GitHub Actions/GitLab CI. |
 
 > *Mẹo tiện dụng: Nếu bạn đã cài đặt toàn cục (`npm i -g synapse-hub`), bạn có thể gõ ngắn gọn `synapse-hub <lệnh>` hoặc các bí danh `synapse`, `agent-qa`.*
 
@@ -249,8 +250,8 @@ flowchart TD
 | **`live-explorer`** | Khảo sát trực tiếp DOM/AOM qua Playwright headless, tự động ngăn chặn thao tác phá hỏng hoặc nguy hiểm. | `playwright-live-interaction`, `self-healing-locator`, `visual-regression-sentinel` | `safety_firewall.py`, `browser_helpers.js` |
 | **`pom-crafter`** | Kỹ sư Clean POM, kiểm tra breaking change API, sinh test từ User Story. | `clean-pom-crafter`, `lam-script-generator`, `synthetic-test-data-generator` | `generate_tc_from_story.py`, `api_drift_sentinel.py` |
 | **`test-runner`** | Quản lý chạy test headless CLI, chia tải song song CI, lọc log thông minh. | `katalon-cli-runner`, `e2e-testing-patterns`, `flaky-test-sentinel-and-quarantine` | `matrix_sharder.py`, `distill_log.py`, `pinpoint_failure.py` |
-| **`failure-analyst`** | Phân tích nguyên nhân gốc rễ (RCA) khi test thất bại, tự động đề xuất vá locator. | `failure-autopsy-and-healing`, `token-and-context-optimizer` | `auto_heal.py`, `bug_reporter.py`, `cache_resolver.py` |
-| **`quality-gatekeeper`**| Chốt chặn kiểm soát chất lượng, kiểm định 9 Cổng DoD và độ nhạy assertion. | `antigravity-test-sentinel`, `wcag-audit-patterns`, `security-dast-sentinel` | `verify_all.py`, `micro_mutator.py`, `infer_linter.py` |
+| **`failure-analyst`** | Phân tích nguyên nhân gốc rễ (RCA) khi test thất bại, tự động đề xuất vá locator và vòng lặp Reflexion $K=3$. | `failure-autopsy-and-healing`, `token-and-context-optimizer` | `auto_heal.py`, `bug_reporter.py`, `cache_resolver.py`, `auto_heal_reflexion.py` |
+| **`quality-gatekeeper`**| Chốt chặn kiểm soát chất lượng, kiểm định 10 Cổng DoD và độ nhạy assertion. | `antigravity-test-sentinel`, `wcag-audit-patterns`, `security-dast-sentinel` | `verify_all.py`, `micro_mutator.py`, `infer_linter.py`, `skill_collision_guard.py` |
 
 ---
 
@@ -264,7 +265,7 @@ flowchart TD
 | 1 | `clean-pom-crafter` | Thiết kế Page Classes chuẩn Clean POM & Flat Architecture (zero locator trong test script). |
 | 2 | `playwright-live-interaction` | Khảo sát trực tiếp DOM/AOM, kiểm định selector < 200ms qua Playwright Headless. |
 | 3 | `failure-autopsy-and-healing` | Phân tích nguyên nhân lỗi từ JUnit XML/Screenshot, tự động vá locator hỏng. |
-| 4 | `antigravity-test-sentinel` | Chốt chặn kiểm soát chất lượng, phát hiện pass ảo và bảo đảm tuân thủ 9 cổng DoD. |
+| 4 | `antigravity-test-sentinel` | Chốt chặn kiểm soát chất lượng, phát hiện pass ảo và bảo đảm tuân thủ 10 cổng DoD. |
 | 5 | `token-and-context-optimizer` | Tối ưu hóa prompt context, cô đọng log và chống suy giảm ngữ cảnh (Context Rot). |
 | 6 | `flaky-test-sentinel-and-quarantine` | Phát hiện test chập chờn, tính điểm flakiness và quản lý vòng đời cách ly. |
 | 7 | `api-spec-to-e2e-matrix` | Chuyển đổi đặc tả OpenAPI/Swagger thành ma trận kiểm thử E2E (Happy, Boundary, Fault). |
@@ -304,7 +305,7 @@ flowchart TD
 | 41 | `technical-debt-harvester` | Quét và gom toàn bộ comment `shortcut:` thành sổ nợ kỹ thuật có kiểm soát qua lệnh `agent-qa debt`. |
 | 42 | `lean-impact-scoreboard` | Hiển thị bảng điểm đo lường hiệu quả tinh gọn code, token và thời gian phản hồi. |
 
-> **Nguồn mở & credit:** Kỹ năng 31–42 được kế thừa và phát triển từ các dự án mã nguồn mở (andrej-karpathy-skills, ponytail, planning-with-files, anthropics/skills, superpowers, wshobson/agents) — license và tác giả chi tiết tại file `NOTICE` (mục 16–21); hướng dẫn công cụ ngoài kèm theo tại `docs/adopted-ecosystem-tools.md`.
+> **Nguồn mở & credit:** Kỹ năng và công cụ được kế thừa và phát triển từ các dự án mã nguồn mở tiêu biểu (NVIDIA SkillSpector, andrej-karpathy-skills, ponytail, planning-with-files, anthropics/skills, superpowers, wshobson/agents, vercel-labs/agent-browser, LaVague, graphify...) — toàn bộ danh mục bản quyền, license và tác giả chi tiết tại file `NOTICE` (mục 1–33); hướng dẫn công cụ ngoài kèm theo tại `docs/adopted-ecosystem-tools.md`.
 
 </details>
 
@@ -312,13 +313,13 @@ flowchart TD
 
 ## 🛠️ 8. Bộ Công Cụ Dòng Lệnh CLI (tools/)
 
-Dự án đi kèm hơn 60 công cụ tiện ích viết hoàn toàn bằng **thư viện chuẩn Python** (Standard Library), không phụ thuộc package ngoài:
+Dự án đi kèm hơn 68 công cụ tiện ích viết hoàn toàn bằng **thư viện chuẩn Python** (Standard Library), không phụ thuộc package ngoài:
 
 ```bash
 # 1. Chẩn đoán môi trường hệ thống (Node, Python, Chrome, Git)
 npx synapse-hub doctor
 
-# 2. Kiểm tra 9 Cổng Chất Lượng DoD
+# 2. Kiểm tra 10 Cổng Chất Lượng DoD (Gate 0–9)
 npx synapse-hub verify
 
 # 3. Quét phát hiện test pass ảo và ngoại lệ bị bỏ qua ngầm
@@ -335,6 +336,21 @@ npx synapse-hub mutate ./tests
 
 # 7. Dò tìm và cách ly test chập chờn (Flaky Tests)
 npx synapse-hub flaky scan ./tests
+
+# 8. Tra cứu thư viện PageClass lưu trữ vĩnh cửu (Voyager SkillVault)
+python tools/skill_vault.py --query "table_pagination"
+
+# 9. Tự động sửa lỗi kịch bản qua vòng lặp phản hồi Reflexion (K=3)
+python tools/auto_heal_reflexion.py --test "TC_Checkout_01" --error "ElementClickInterceptedException"
+
+# 10. Thẩm vấn và làm rõ yêu cầu nghiệp vụ mập mờ (Pocock Grilling)
+python tools/interview_story.py "As a user I want to checkout"
+
+# 11. Tối ưu câu lệnh assert chống mutant (TextGrad Optimizer)
+python tools/textgrad_mutation_optimizer.py --file tests/test_login.py
+
+# 12. Đo lường độ chính xác gọi tool của AI Agent (Gorilla BFCL Benchmark)
+python tools/synapse_qa_bench.py
 ```
 
 *(Xem toàn bộ hướng dẫn tham số chi tiết tại [docs/CLI_REFERENCE.md](docs/CLI_REFERENCE.md) và [tools/TOOLS_RUNBOOK.md](tools/TOOLS_RUNBOOK.md)).*

package/docs/ARCHITECTURE.md

@@ -1,7 +1,7 @@
 # Agent-Skills Architecture & Design Principles
 
 > **Scope:** Enterprise Multi-Agent QA Hub  
-> **Version:** `2.5.0` | **Status:** Active / Production Standard
+> **Version:** `2.6.0` | **Status:** Active / Production Standard
 
 ---
 
@@ -69,9 +69,9 @@ Test automation scripts orchestrated through this Hub enforce strict Clean POM b
 
 ---
 
-## 4. The 9 Quality Gates Definition-of-Done (DoD)
+## 4. The 10 Quality Gates Definition-of-Done (DoD)
 
-All automated test code authored, modified, or refactored by AI agents must pass through the deterministic 9 Quality Gates pipeline (`tools/verify_all.py`) prior to committing or merging:
+All automated test code authored, modified, or refactored by AI agents must pass through the deterministic 10 Quality Gates pipeline (`tools/verify_all.py`) prior to committing or merging:
 
 | Gate | Title | Verifier Tool | Strict Acceptance Criteria |
 | :---: | :--- | :--- | :--- |
@@ -84,6 +84,7 @@ All automated test code authored, modified, or refactored by AI agents must pass
 | **Gate 6** | **Credential Security** | `verify_all.py` | AST regex scan blocking hardcoded passwords, private keys, and secret tokens in code. |
 | **Gate 7** | **Static Defect & Fake-Pass Sentinel** | `infer_linter.py` | Detects 0-assertion tests, swallowed exception blocks (`except: pass`), hard sleeps, and unawaited promises. |
 | **Gate 8** | **Assertion Sensitivity Sentinel** | `micro_mutator.py` | Syntactic micro-mutations linked via variable dataflow; requires Sensitivity Score $\ge 80\%$. |
+| **Gate 9** | **Tier-2 Skill Routing & Collision Guard** | `skill_collision_guard.py` | Audits skill trigger descriptions and vectors; blocks ambiguous activation with semantic overlap $\ge 0.75$. |
 
 ---
 
@@ -99,12 +100,12 @@ The Hub equips 6 specialized subagents with scoped tool and skill permissions:
 
 | Subagent Role | Primary Focus | Allowed Skills | Execution Tools |
 | :--- | :--- | :--- | :--- |
-| **`orchestrator`** | Task decomposition & governance | `agent-orchestration-multi-agent-optimize`, `graphify-impact-analyzer`, `architecture-decision-records`, `token-and-context-optimizer` | `verify_all.py`, `test_impact.py`, `setup_project.py` |
-| **`pom-crafter`** | Clean POM design & test generation | `clean-pom-crafter`, `lam-script-generator`, `synthetic-test-data-generator`, `api-spec-to-e2e-matrix` | `lookup_xpath.py`, `repo_map.py`, `generate_tc_from_story.py` |
+| **`orchestrator`** | Task decomposition & governance | `agent-orchestration-multi-agent-optimize`, `graphify-impact-analyzer`, `architecture-decision-records`, `token-and-context-optimizer` | `verify_all.py`, `test_impact.py`, `setup_project.py`, `interview_story.py`, `dspy_qa_signatures.py` |
+| **`pom-crafter`** | Clean POM design & test generation | `clean-pom-crafter`, `lam-script-generator`, `synthetic-test-data-generator`, `api-spec-to-e2e-matrix` | `lookup_xpath.py`, `repo_map.py`, `generate_tc_from_story.py`, `skill_vault.py` |
 | **`live-explorer`** | Live DOM & AOM exploration (<200ms) | `playwright-live-interaction`, `self-healing-locator`, `visual-regression-sentinel`, `api-network-mocking-interception` | `browser_helpers.js`, `e2e_flow_prober.ps1`, `safety_firewall.py` |
-| **`test-runner`** | Headless CLI test execution & CI | `katalon-cli-runner`, `e2e-testing-patterns`, `flaky-test-sentinel-and-quarantine`, `backend-load-and-stress-patterns`, `github-actions-templates` | `matrix_sharder.py`, `distill_log.py`, `pinpoint_failure.py`, `flaky_detector.py` |
-| **`failure-analyst`**| Visual & XML error autopsy | `failure-autopsy-and-healing`, `self-healing-locator`, `file-and-report-validator` | `auto_heal.py`, `heal_pr_automator.py`, `pinpoint_failure.py`, `cache_resolver.py` |
-| **`quality-gatekeeper`**| 9 Gates DoD & Fake-Pass Sentinel | `antigravity-test-sentinel`, `code-refactoring-refactor-clean`, `wcag-audit-patterns`, `web-vitals-and-performance-profiler`, `security-dast-sentinel` | `verify_all.py`, `infer_linter.py`, `micro_mutator.py`, `trace_data_flow.py` |
+| **`test-runner`** | Headless CLI test execution & CI | `katalon-cli-runner`, `e2e-testing-patterns`, `flaky-test-sentinel-and-quarantine`, `backend-load-and-stress-patterns`, `github-actions-templates` | `matrix_sharder.py`, `distill_log.py`, `pinpoint_failure.py`, `flaky_detector.py`, `reversible_sandbox.py`, `synapse_qa_bench.py` |
+| **`failure-analyst`**| Visual & XML error autopsy | `failure-autopsy-and-healing`, `self-healing-locator`, `file-and-report-validator` | `auto_heal.py`, `heal_pr_automator.py`, `pinpoint_failure.py`, `cache_resolver.py`, `auto_heal_reflexion.py` |
+| **`quality-gatekeeper`**| 10 Gates DoD & Fake-Pass Sentinel | `antigravity-test-sentinel`, `code-refactoring-refactor-clean`, `wcag-audit-patterns`, `web-vitals-and-performance-profiler`, `security-dast-sentinel` | `verify_all.py`, `infer_linter.py`, `micro_mutator.py`, `trace_data_flow.py`, `skill_collision_guard.py`, `textgrad_mutation_optimizer.py` |
 
 ---
 
@@ -115,4 +116,31 @@ To ensure consistency across various distribution registries and developer inter
 - **NPM Package & Antigravity Plugin:** `synapse-hub` (distributed on NPM Registry and Antigravity Marketplace)
 - **Python Package & Universal CLI:** `agent-qa` (PEP 621 package on PyPI providing the `agent-qa` CLI binary)
 - **MCP Server Protocol Services:** `enterprise-agent-qa` (Core QA MCP server) and `synapse-mcp-excel` (Excel tool server)
-- **Skill Catalog Manifest:** `enterprise-agent-skills-hub` (internal catalog schema identifier in `skills_manifest.json`)
+- **Skill Catalog Manifest:** `enterprise-agent-skills-hub` (internal catalog schema identifier in `skills_manifest.json`) and `agentskills.json` (AgentSkills v1 open standard)
+
+---
+
+## 7. Autonomous Agent Self-Evolution & Training Subsystems
+
+To elevate AI testing beyond static prompt engineering, Synapse Hub incorporates 6 advanced agent training, compilation, and self-evolution mechanisms synthesized from modern agentic architectures:
+
+```mermaid
+flowchart TD
+    subgraph SelfEvolution["Autonomous Agent Self-Evolution Subsystem"]
+        Vault["<b>Voyager Lifelong Vault</b><br/>(skill_vault.py)<br/>• Verified PageClass SQLite memory<br/>• Zero repetitive prompt re-synthesis"]
+        Reflexion["<b>Episodic Reflexion Loop</b><br/>(auto_heal_reflexion.py)<br/>• K=3 trial-feedback learning<br/>• Self-healing without git pollution"]
+        DSPy["<b>DSPy Declarative QA Engine</b><br/>(dspy_qa_signatures.py)<br/>• Typed QA signatures<br/>• Eliminates brittle prompt hacking"]
+        TextGrad["<b>TextGrad Mutation Loss</b><br/>(textgrad_mutation_optimizer.py)<br/>• AST mutants as loss function<br/>• Optimizes assertions to score &ge; 80%"]
+        Reversible["<b>GoEx Reversible Sandbox</b><br/>(reversible_sandbox.py)<br/>• LIFO undo execution stack<br/>• Zero leftover test debris"]
+        Bench["<b>Gorilla BFCL Benchmark</b><br/>(synapse_qa_bench.py)<br/>• Evaluates function calling fidelity<br/>• Prevents agent regression"]
+    end
+
+    Vault --> DSPy --> TextGrad --> Reversible --> Reflexion --> Bench
+```
+
+1. **Lifelong Skill Memory (`skill_vault.py`):** Inspired by Voyager, stores verified POM methods and complex interaction patterns in permanent SQLite memory, growing the agent's capability with every run.
+2. **Episodic Trial-Feedback (`auto_heal_reflexion.py`):** Implements Noah Shinn's Reflexion framework, enabling agents to evaluate test failure traces across $K=3$ iterations, generating textual self-reflection to correct locator strategies.
+3. **Declarative Signature Compilation (`dspy_qa_signatures.py`):** Adheres to Stanford DSPy principles, compiling prompt templates into structured, typed input-output signatures.
+4. **Mutant-Directed Loss Optimization (`textgrad_mutation_optimizer.py`):** Treats surviving AST mutants as a loss function (TextGrad), iteratively refining assertion logic until all mutants are killed.
+5. **Reversible Execution Teardown (`reversible_sandbox.py`):** Implements GoEx-style reversible rollback stacks for filesystem and database mutations during automated exploratory runs.
+6. **Tool Function Calling Benchmark (`synapse_qa_bench.py`):** Implements Berkeley Function-Calling Leaderboard (BFCL) standards for enterprise QA tools, benchmarking tool selection precision and multi-turn execution accuracy.

package/docs/adopted-ecosystem-tools.md

@@ -85,3 +85,12 @@ Local model gateway (default `127.0.0.1:3456`) with routing, retry, failover, an
 
 - **Security note:** it is a man-in-the-middle for API keys — run strictly local, never expose the port, and audit its config before pointing production credentials at it.
 - Hub use: route mechanical subagent work to cheaper models while keeping strong models for synthesis/review; its request logs match the hub telemetry fields (token in/out, cost).
+
+## 9. ponytail (DietrichGebert/ponytail) — MIT
+
+Lazy senior developer plugin for Claude Code and agentic coding workflows.
+
+- **Provenance:** Created by DietrichGebert (<https://github.com/DietrichGebert/ponytail>) under the MIT License.
+- **Hub Inspiration:** Core concepts adapted into Synapse-Hub include the 7-rung reuse ladder (`lean-code-ladder`), technical debt harvesting (`technical-debt-harvester` & `tools/debt_harvester.py`), 6-pillar code review (`senior-code-review` & `tools/senior_code_review.py`), and whole-repo audit (`repo-quality-audit`).
+- **Hub Adaptations:** Re-scoped specifically for enterprise automated testing suites, Clean POM architecture, and 0-token AST verification.
+