specky-sdd 3.7.2 → 3.8.0

package/.apm/skills/specky-onboarding/SKILL.md

@@ -47,17 +47,17 @@ Check for:
 |-------|-------|---------|
 | @specky-onboarding | Pre | Interactive wizard and help |
 | @specky-orchestrator | All | Full pipeline coordinator |
-| @sdd-init | 0 | Initialize pipeline + create spec branch |
-| @research-analyst | 1 | Codebase scan + discovery |
-| @spec-engineer | 2 | Write SPECIFICATION.md with EARS |
-| @sdd-clarify | 3 | Resolve ambiguities + EARS validation |
-| @design-architect | 4 | Write DESIGN.md + diagrams |
-| @task-planner | 5 | Write TASKS.md + CHECKLIST.md |
-| @quality-reviewer | 6 | Completeness audit + compliance |
-| @implementer | 7 | Implementation plan + test stubs + IaC |
-| @test-verifier | 8 | Coverage + drift + phantom detection |
-| @requirements-engineer | Pre | FRD + NFRD from raw input |
-| @release-engineer | 9 | Gates + PR + docs + work items |
+| @specky-sdd-init | 0 | Initialize pipeline + create spec branch |
+| @specky-research-analyst | 1 | Codebase scan + discovery |
+| @specky-spec-engineer | 2 | Write SPECIFICATION.md with EARS |
+| @specky-sdd-clarify | 3 | Resolve ambiguities + EARS validation |
+| @specky-design-architect | 4 | Write DESIGN.md + diagrams |
+| @specky-task-planner | 5 | Write TASKS.md + CHECKLIST.md |
+| @specky-quality-reviewer | 6 | Completeness audit + compliance |
+| @specky-implementer | 7 | Implementation plan + test stubs + IaC |
+| @specky-test-verifier | 8 | Coverage + drift + phantom detection |
+| @specky-requirements-engineer | Pre | FRD + NFRD from raw input |
+| @specky-release-engineer | 9 | Gates + PR + docs + work items |
 
 ## All 22 Prompts
 
@@ -95,14 +95,14 @@ Check for:
 
 | Skill | Triggers On |
 |-------|-------------|
-| sdd-pipeline | "specky", "SDD pipeline", "EARS notation", "pipeline phases" |
+| specky-sdd-pipeline | "specky", "SDD pipeline", "EARS notation", "pipeline phases" |
 | specky-orchestrator | "orchestrate", "run full pipeline", "advance phase" |
 | specky-onboarding | "help", "get started", "what is specky" |
 | implementer | "implementation plan", "test stubs", "IaC generation" |
 | test-verifier | "verify tests", "check coverage", "phantom detection" |
 | release-engineer | "prepare release", "create PR", "release gates" |
 | research-analyst | "research codebase", "scan tech stack", "import documents" |
-| sdd-markdown-standard | "artifact format", "spec formatting" |
+| specky-sdd-markdown-standard | "artifact format", "spec formatting" |
 
 ## 58 MCP Tools by Category
 
@@ -135,21 +135,21 @@ Check for:
 ## 16 Hook Scripts
 
 **Blocking (exit 2 = halt):**
-- artifact-validator.sh — Prerequisite .md files exist
-- phase-gate.sh — Output artifact created with quality
-- security-scan.sh — OWASP + secrets scan
-- release-gate.sh — 90% pass rate + artifact checks
+- specky-artifact-validator.sh — Prerequisite .md files exist
+- specky-phase-gate.sh — Output artifact created with quality
+- specky-security-scan.sh — OWASP + secrets scan
+- specky-release-gate.sh — 90% pass rate + artifact checks
 
 **Advisory (exit 0 = warn):**
-- branch-validator.sh — Branch matches phase expectations
-- pipeline-guard.sh — Pipeline ordering / phase-skip guard
-- lgtm-gate.sh — Human review reminder at Phases 2/4/5
-- session-banner.sh — Session start pipeline-status banner
-- spec-sync.sh — Detect spec-code drift
-- auto-checkpoint.sh — Suggest checkpoint after writes
-- spec-quality.sh — Specification quality metrics
-- ears-validator.sh — EARS pattern compliance
-- task-tracer.sh — Task dependency graph
-- drift-monitor.sh — CONSTITUTION drift detection
-- cognitive-debt-alert.sh — Cognitive surrender detection
-- metrics-dashboard.sh — Quality metrics collection
+- specky-branch-validator.sh — Branch matches phase expectations
+- specky-pipeline-guard.sh — Pipeline ordering / phase-skip guard
+- specky-lgtm-gate.sh — Human review reminder at Phases 2/4/5
+- specky-session-banner.sh — Session start pipeline-status banner
+- specky-spec-sync.sh — Detect spec-code drift
+- specky-auto-checkpoint.sh — Suggest checkpoint after writes
+- specky-spec-quality.sh — Specification quality metrics
+- specky-ears-validator.sh — EARS pattern compliance
+- specky-task-tracer.sh — Task dependency graph
+- specky-drift-monitor.sh — CONSTITUTION drift detection
+- specky-cognitive-debt-alert.sh — Cognitive surrender detection
+- specky-metrics-dashboard.sh — Quality metrics collection

package/.apm/skills/specky-orchestrator/SKILL.md

@@ -15,16 +15,16 @@ Model guidance is capability-based: fast, balanced, and reasoning-focused. Do no
 
 | Phase | Agent | Recommended Class | MCP Tools | Required Input | Output Artifact |
 |-------|-------|-------------------|-----------|----------------|-----------------|
-| 0 Init | @sdd-init | Fast | sdd_init, sdd_scan_codebase | — | CONSTITUTION.md, .sdd-state.json |
-| 1 Discover | @research-analyst | Balanced | sdd_discover, sdd_research, sdd_import_document, sdd_import_transcript, sdd_check_ecosystem | CONSTITUTION.md | RESEARCH.md |
-| 2 Specify | @spec-engineer | Reasoning-focused | sdd_write_spec, sdd_turnkey_spec, sdd_validate_ears, sdd_figma_to_spec | RESEARCH.md | SPECIFICATION.md |
-| 3 Clarify | @sdd-clarify | Reasoning-focused | sdd_clarify, sdd_validate_ears, sdd_turnkey_spec | SPECIFICATION.md | Updates to SPECIFICATION.md |
-| 4 Design | @design-architect | Reasoning-focused | sdd_write_design, sdd_generate_all_diagrams, sdd_generate_diagram | SPECIFICATION.md | DESIGN.md |
-| 5 Tasks | @task-planner | Balanced | sdd_write_tasks, sdd_checklist | DESIGN.md | TASKS.md, CHECKLIST.md |
-| 6 Analyze | @quality-reviewer | Balanced | sdd_run_analysis, sdd_cross_analyze, sdd_compliance_check, sdd_check_sync | TASKS.md, CHECKLIST.md | ANALYSIS.md, COMPLIANCE.md |
-| 7 Implement | @implementer | Balanced | sdd_implement, sdd_generate_tests, sdd_generate_pbt, sdd_generate_iac, sdd_generate_dockerfile | ANALYSIS.md | Code scaffolding, test stubs |
-| 8 Verify | @test-verifier | Reasoning-focused | sdd_verify_tests, sdd_verify_tasks, sdd_check_sync, sdd_validate_ears | SPECIFICATION.md, TASKS.md | VERIFICATION.md, CROSS_ANALYSIS.md |
-| 9 Release | @release-engineer | Fast | sdd_create_pr, sdd_generate_all_docs, sdd_export_work_items | ANALYSIS.md (APPROVE) | PR, docs, work items |
+| 0 Init | @specky-sdd-init | Fast | sdd_init, sdd_scan_codebase | — | CONSTITUTION.md, .sdd-state.json |
+| 1 Discover | @specky-research-analyst | Balanced | sdd_discover, sdd_research, sdd_import_document, sdd_import_transcript, sdd_check_ecosystem | CONSTITUTION.md | RESEARCH.md |
+| 2 Specify | @specky-spec-engineer | Reasoning-focused | sdd_write_spec, sdd_turnkey_spec, sdd_validate_ears, sdd_figma_to_spec | RESEARCH.md | SPECIFICATION.md |
+| 3 Clarify | @specky-sdd-clarify | Reasoning-focused | sdd_clarify, sdd_validate_ears, sdd_turnkey_spec | SPECIFICATION.md | Updates to SPECIFICATION.md |
+| 4 Design | @specky-design-architect | Reasoning-focused | sdd_write_design, sdd_generate_all_diagrams, sdd_generate_diagram | SPECIFICATION.md | DESIGN.md |
+| 5 Tasks | @specky-task-planner | Balanced | sdd_write_tasks, sdd_checklist | DESIGN.md | TASKS.md, CHECKLIST.md |
+| 6 Analyze | @specky-quality-reviewer | Balanced | sdd_run_analysis, sdd_cross_analyze, sdd_compliance_check, sdd_check_sync | TASKS.md, CHECKLIST.md | ANALYSIS.md, COMPLIANCE.md |
+| 7 Implement | @specky-implementer | Balanced | sdd_implement, sdd_generate_tests, sdd_generate_pbt, sdd_generate_iac, sdd_generate_dockerfile | ANALYSIS.md | Code scaffolding, test stubs |
+| 8 Verify | @specky-test-verifier | Reasoning-focused | sdd_verify_tests, sdd_verify_tasks, sdd_check_sync, sdd_validate_ears | SPECIFICATION.md, TASKS.md | VERIFICATION.md, CROSS_ANALYSIS.md |
+| 9 Release | @specky-release-engineer | Fast | sdd_create_pr, sdd_generate_all_docs, sdd_export_work_items | ANALYSIS.md (APPROVE) | PR, docs, work items |
 
 ## Hook Enforcement Matrix
 
@@ -32,34 +32,34 @@ Model guidance is capability-based: fast, balanced, and reasoning-focused. Do no
 
 | Tool Matcher | Hooks | Type |
 |-------------|-------|------|
-| sdd_init | branch-validator | Advisory |
-| sdd_discover, sdd_research, sdd_import_* | artifact-validator, branch-validator | Blocking + Advisory |
-| sdd_write_spec, sdd_turnkey_spec, sdd_figma_to_spec | artifact-validator, branch-validator | Blocking + Advisory |
-| sdd_write_design, sdd_generate_all_diagrams | artifact-validator, branch-validator | Blocking + Advisory |
-| sdd_write_tasks, sdd_checklist | artifact-validator, branch-validator | Blocking + Advisory |
-| sdd_implement, sdd_generate_tests | artifact-validator, branch-validator | Blocking + Advisory |
-| sdd_verify_tests, sdd_verify_tasks | artifact-validator, branch-validator | Blocking + Advisory |
-| sdd_run_analysis, sdd_cross_analyze | artifact-validator, branch-validator | Blocking + Advisory |
-| sdd_create_pr | artifact-validator, branch-validator, security-scan, release-gate | All Blocking |
+| sdd_init | specky-branch-validator | Advisory |
+| sdd_discover, sdd_research, sdd_import_* | specky-artifact-validator, specky-branch-validator | Blocking + Advisory |
+| sdd_write_spec, sdd_turnkey_spec, sdd_figma_to_spec | specky-artifact-validator, specky-branch-validator | Blocking + Advisory |
+| sdd_write_design, sdd_generate_all_diagrams | specky-artifact-validator, specky-branch-validator | Blocking + Advisory |
+| sdd_write_tasks, sdd_checklist | specky-artifact-validator, specky-branch-validator | Blocking + Advisory |
+| sdd_implement, sdd_generate_tests | specky-artifact-validator, specky-branch-validator | Blocking + Advisory |
+| sdd_verify_tests, sdd_verify_tasks | specky-artifact-validator, specky-branch-validator | Blocking + Advisory |
+| sdd_run_analysis, sdd_cross_analyze | specky-artifact-validator, specky-branch-validator | Blocking + Advisory |
+| sdd_create_pr | specky-artifact-validator, specky-branch-validator, specky-security-scan, specky-release-gate | All Blocking |
 
 ### Post-Phase Hooks (validate after tool runs)
 
 | Tool Matcher | Hooks | Type |
 |-------------|-------|------|
-| sdd_init | phase-gate, auto-checkpoint | Blocking + Advisory |
-| sdd_write_spec, sdd_turnkey_spec | phase-gate, spec-quality, ears-validator, lgtm-gate, spec-sync, auto-checkpoint | Mixed |
-| sdd_write_design | phase-gate, spec-sync, lgtm-gate, auto-checkpoint | Mixed |
-| sdd_write_tasks | phase-gate, task-tracer, lgtm-gate, spec-sync, auto-checkpoint | Mixed |
-| sdd_implement, sdd_generate_tests | spec-sync, auto-checkpoint | Advisory |
-| sdd_verify_tests, sdd_verify_tasks | phase-gate, drift-monitor | Mixed |
-| sdd_run_analysis, sdd_cross_analyze | phase-gate, cognitive-debt-alert, metrics-dashboard, drift-monitor | Mixed |
+| sdd_init | specky-phase-gate, specky-auto-checkpoint | Blocking + Advisory |
+| sdd_write_spec, sdd_turnkey_spec | specky-phase-gate, specky-spec-quality, specky-ears-validator, specky-lgtm-gate, specky-spec-sync, specky-auto-checkpoint | Mixed |
+| sdd_write_design | specky-phase-gate, specky-spec-sync, specky-lgtm-gate, specky-auto-checkpoint | Mixed |
+| sdd_write_tasks | specky-phase-gate, specky-task-tracer, specky-lgtm-gate, specky-spec-sync, specky-auto-checkpoint | Mixed |
+| sdd_implement, sdd_generate_tests | specky-spec-sync, specky-auto-checkpoint | Advisory |
+| sdd_verify_tests, sdd_verify_tasks | specky-phase-gate, specky-drift-monitor | Mixed |
+| sdd_run_analysis, sdd_cross_analyze | specky-phase-gate, specky-cognitive-debt-alert, specky-metrics-dashboard, specky-drift-monitor | Mixed |
 
 ## LGTM Gate Protocol
 
 Phases 2 (Specify), 4 (Design), and 5 (Tasks) require human LGTM before advancing:
 
 1. Phase agent completes and writes artifact
-2. lgtm-gate.sh runs → prints artifact summary
+2. specky-lgtm-gate.sh runs → prints artifact summary
 3. Orchestrator asks: "Review [ARTIFACT]. Reply 'LGTM' to proceed."
 4. If LGTM → call sdd_advance_phase → next agent
 5. If feedback → route back to phase agent for revision
@@ -79,7 +79,7 @@ Phases 2 (Specify), 4 (Design), and 5 (Tasks) require human LGTM before advancin
 
 Before calling sdd_advance_phase, verify:
 1. ✅ Required artifact exists (PHASE_REQUIRED_FILES)
-2. ✅ Artifact has minimum quality (phase-gate.sh passed)
+2. ✅ Artifact has minimum quality (specky-phase-gate.sh passed)
 3. ✅ LGTM received (if phase 2, 4, or 5)
 4. ✅ Branch matches expectations
 5. ✅ Checkpoint created (sdd_checkpoint)

package/.apm/skills/{release-engineer → specky-release-engineer}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: release-engineer
+name: specky-release-engineer
 description: "This skill should be used when the user asks to 'prepare release', 'create PR', 'generate documentation', 'run release gates', or needs guidance on Phase 9 release. Also trigger on 'sdd release', 'blocking gates', 'security scan', 'release gate', or 'export work items'."
 ---
 
@@ -33,11 +33,11 @@ Missing prerequisites block release. Run `/specky:check-gates` to validate.
 
 Two sequential blocking gates must pass before release:
 
-### Gate 1: Security Gate (security-scan.sh)
+### Gate 1: Security Gate (specky-security-scan.sh)
 
 Execute security scanning:
 ```bash
-./scripts/security-scan.sh --full
+./scripts/specky-security-scan.sh --full
 ```
 
 Checks performed:
@@ -56,11 +56,11 @@ Pass criteria:
 
 Fail items block release completely.
 
-### Gate 2: Release Gate (release-gate.sh)
+### Gate 2: Release Gate (specky-release-gate.sh)
 
 Execute final release checklist:
 ```bash
-./scripts/release-gate.sh --version=X.Y.Z
+./scripts/specky-release-gate.sh --version=X.Y.Z
 ```
 
 Verifies:
@@ -260,7 +260,7 @@ Generate from commit history, SPECIFICATION.md, and VERIFICATION.md:
 
 ```
 /specky:release --version=X.Y.Z          # Full release workflow
-/specky:release --security-scan          # Run security gate only
+/specky:release --specky-security-scan          # Run security gate only
 /specky:release --generate-docs          # Generate docs only
 /specky:release --create-pr --no-merge   # Create PR, don't merge
 /specky:release --export-items            # Export to project mgmt
@@ -290,4 +290,4 @@ If post-release issues detected:
 
 ## Companion Agent
 
-**@release-engineer** — Phase 9 agent that runs blocking gates and calls these tools. Load this skill as first step.
+**@specky-release-engineer** — Phase 9 agent that runs blocking gates and calls these tools. Load this skill as first step.

package/.apm/skills/{research-analyst → specky-research-analyst}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: research-analyst
+name: specky-research-analyst
 description: "This skill should be used when the user asks to 'research codebase', 'scan tech stack', 'import documents', 'discovery questions', or needs guidance on Phase 1 research. Also trigger on 'sdd research', 'brownfield scan', 'import transcript', or 'check ecosystem'."
 ---
 
@@ -283,4 +283,4 @@ Structure the research artifact as:
 
 ## Companion Agent
 
-**@research-analyst** — Phase 1 agent that calls these tools to build the knowledge baseline. Load this skill as first step.
+**@specky-research-analyst** — Phase 1 agent that calls these tools to build the knowledge baseline. Load this skill as first step.

package/.apm/skills/{sdd-markdown-standard → specky-sdd-markdown-standard}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: sdd-markdown-standard
+name: specky-sdd-markdown-standard
 description: "This skill should be used when generating or formatting SDD artifacts (CONSTITUTION.md, SPECIFICATION.md, DESIGN.md, TASKS.md, VERIFICATION.md, ANALYSIS.md). Also trigger on 'sdd markdown', 'artifact format', or 'spec formatting'."
 ---
 
@@ -279,4 +279,4 @@ Run markdown linter: `markdownlint sdd-artifacts/`
 
 ## Companion Agent
 
-**@requirements-engineer** — Pre-pipeline agent that produces FRD/NFRD documents using this formatting standard. Load this skill as first step.
+**@specky-requirements-engineer** — Pre-pipeline agent that produces FRD/NFRD documents using this formatting standard. Load this skill as first step.

package/.apm/skills/{sdd-pipeline → specky-sdd-pipeline}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: sdd-pipeline
+name: specky-sdd-pipeline
 description: "This skill should be used when the user asks about 'spec-driven development', 'SDD pipeline', 'specky', 'pipeline phases', 'EARS notation', 'requirements engineering', 'model routing', or needs guidance on the 10-phase SDD workflow (Init → Discover → Specify → Clarify → Design → Tasks → Analyze → Implement → Verify → Release). Also trigger on 'spec this', 'plan this feature', 'break into tasks', 'quality gate', 'constitution', or 'spec sync'."
 ---
 
@@ -79,22 +79,22 @@ For Phase 7 (Implementation), prioritize fast feedback loops over long reasoning
 The pipeline includes 16 automation hooks for customization:
 
 **Blocking Hooks** (workflow stops if hook fails — exit code 2):
-1. `artifact-validator` — Pre-tool: blocks if required artifacts missing
-2. `phase-gate` — Post-tool: blocks if output artifact wasn't created
-3. `security-scan` — Pre-release: blocks if hardcoded secrets detected
-4. `release-gate` — Pre-release: blocks if gate conditions not met
+1. `specky-artifact-validator` — Pre-tool: blocks if required artifacts missing
+2. `specky-phase-gate` — Post-tool: blocks if output artifact wasn't created
+3. `specky-security-scan` — Pre-release: blocks if hardcoded secrets detected
+4. `specky-release-gate` — Pre-release: blocks if gate conditions not met
 
 **Advisory Hooks** (workflow continues; failures logged):
-1. `branch-validator` — Pre-tool: warns if wrong branch for phase
-2. `spec-sync` — Post-tool: checks spec-code drift
-3. `auto-checkpoint` — Post-tool: suggests checkpoint after artifact changes
-4. `spec-quality` — Post-spec: validates specification quality
-5. `task-tracer` — Post-tasks: traces task dependencies
-6. `ears-validator` — Post-spec: validates EARS notation patterns
-7. `lgtm-gate` — Post-spec/design/tasks: pauses for human LGTM
-8. `drift-monitor` — Post-verify/review: monitors specification drift
-9. `cognitive-debt-alert` — Post-analysis: flags cognitive debt metrics
-10. `metrics-dashboard` — Post-analysis: updates metrics dashboard
+1. `specky-branch-validator` — Pre-tool: warns if wrong branch for phase
+2. `specky-spec-sync` — Post-tool: checks spec-code drift
+3. `specky-auto-checkpoint` — Post-tool: suggests checkpoint after artifact changes
+4. `specky-spec-quality` — Post-spec: validates specification quality
+5. `specky-task-tracer` — Post-tasks: traces task dependencies
+6. `specky-ears-validator` — Post-spec: validates EARS notation patterns
+7. `specky-lgtm-gate` — Post-spec/design/tasks: pauses for human LGTM
+8. `specky-drift-monitor` — Post-verify/review: monitors specification drift
+9. `specky-cognitive-debt-alert` — Post-analysis: flags cognitive debt metrics
+10. `specky-metrics-dashboard` — Post-analysis: updates metrics dashboard
 
 Hooks are configured in `sdd-hooks.json` with PreToolUse and PostToolUse matchers.
 
@@ -127,9 +127,9 @@ Hooks are configured in `sdd-hooks.json` with PreToolUse and PostToolUse matcher
 **Agent-based:**
 ```
 @specky-orchestrator           (end-to-end pipeline coordinator)
-@sdd-init feature-name         (Phase 0 — initialize feature)
-@spec-engineer                 (Phase 2 — write SPECIFICATION.md)
-@implementer                   (Phase 7 — scaffold code + tests)
+@specky-sdd-init feature-name         (Phase 0 — initialize feature)
+@specky-spec-engineer                 (Phase 2 — write SPECIFICATION.md)
+@specky-implementer                   (Phase 7 — scaffold code + tests)
 ```
 
 See [copilot-instructions.instructions.md](../../instructions/copilot-instructions.instructions.md) for the full agent catalog.
@@ -179,7 +179,7 @@ spec/003-notifs    ──→    ↑
 git checkout develop
 git pull origin develop
 git checkout -b spec/001-user-authentication
-# Run @sdd-init / /specky-greenfield
+# Run @specky-sdd-init / /specky-greenfield
 ```
 
 **After Phase 7 passes:**
@@ -195,7 +195,7 @@ git push origin develop
 git checkout stage
 git merge --no-ff develop
 git push origin stage
-# Run @release-engineer for blocking gates
+# Run @specky-release-engineer for blocking gates
 ```
 
 **Releasing to production:**
@@ -228,13 +228,13 @@ git push origin main --tags
 |-------|-------|-------------------|
 | Pre | @specky-onboarding | Fast |
 | All | @specky-orchestrator | Balanced |
-| 0 | @sdd-init | Fast |
-| 1 | @research-analyst | Balanced |
-| 2 | @spec-engineer | Reasoning-focused |
-| 3 | @sdd-clarify | Reasoning-focused |
-| 4 | @design-architect | Reasoning-focused |
-| 5 | @task-planner | Balanced |
-| 6 | @quality-reviewer | Balanced |
-| 7 | @implementer | Balanced |
-| 8 | @test-verifier | Reasoning-focused |
-| 9 | @release-engineer | Fast |
+| 0 | @specky-sdd-init | Fast |
+| 1 | @specky-research-analyst | Balanced |
+| 2 | @specky-spec-engineer | Reasoning-focused |
+| 3 | @specky-sdd-clarify | Reasoning-focused |
+| 4 | @specky-design-architect | Reasoning-focused |
+| 5 | @specky-task-planner | Balanced |
+| 6 | @specky-quality-reviewer | Balanced |
+| 7 | @specky-implementer | Balanced |
+| 8 | @specky-test-verifier | Reasoning-focused |
+| 9 | @specky-release-engineer | Fast |

package/.apm/skills/{test-verifier → specky-test-verifier}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: test-verifier
+name: specky-test-verifier
 description: "This skill should be used when the user asks to 'verify tests', 'check coverage', 'detect phantom completions', 'check spec drift', or needs guidance on Phase 8 verification. Also trigger on 'sdd test', 'test traceability', 'verification report', or 'gate criteria'."
 ---
 
@@ -214,4 +214,4 @@ Produce standardized verification artifact:
 
 ## Companion Agent
 
-**@test-verifier** — Phase 8 agent that calls these tools in sequence. Load this skill as first step.
+**@specky-test-verifier** — Phase 8 agent that calls these tools in sequence. Load this skill as first step.

package/CHANGELOG.md

@@ -7,6 +7,81 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [3.8.0] - 2026-07-07
+
+Wave 1 multi-harness APM targets (Cursor, OpenCode, Agent Skills) plus a multi-feature phase-advancement fix.
+
+### Added
+
+- Wave 1 APM target support for `cursor`, `opencode`, and `agent-skills`, including target-native compiler registration, install paths, MCP config writers, and regression coverage.
+- `specky install --target=<targets>` as the canonical APM-aligned install selector. The legacy `--ide` flag remains as a deprecated alias for backward compatibility.
+- `specky compile --target=<targets>` for compiling instruction primitives into root context files (`.github/copilot-instructions.md`, `CLAUDE.md`, or `AGENTS.md`).
+- `.markdownlint.json` configuration codifying the repository's Markdown conventions (Keep a Changelog sibling headings, intentional inline HTML in `README.md`) so documentation lint is clean.
+- Regression test verifying that pre-existing Claude hooks in `.claude/settings.json` are removed when Copilot is installed into the same workspace, while non-hook user settings are preserved.
+
+### Changed
+
+- **All APM primitives are now namespaced with a `specky-` prefix** (agents, skills, and hook scripts; prompts already carried the prefix) to avoid collisions with other packages installed in the same workspace. Agent mentions change accordingly (for example `@spec-engineer` is now `@specky-spec-engineer`). The Copilot instruction primitive keeps the reserved `.github/copilot-instructions.md` filename.
+- `specky doctor` now validates installed `targets[]` metadata instead of assuming only Copilot/Claude IDE scopes.
+- Copilot-inclusive installs strip Claude hooks from `.claude/settings.json` even when installing both Copilot and Claude assets, preventing Copilot hook cross-read blocks.
+- APM manifest and policy now use canonical target names and include Cursor/OpenCode target isolation checks.
+
+### Fixed
+
+- Fixed multi-feature phase advancement so artifact validation uses the requested feature number instead of always validating `state.features[0]`.
+- Confirmed existing diagram persistence and REQ-ID test generation regressions remain covered by passing tests.
+
+## [3.7.3] - 2026-07-07
+
+APM governance, primitive lockfiles, and enterprise package validation.
+
+### Added
+
+- APM governance commands: `specky apm validate`, `specky apm lock`, `specky apm verify-lock`, `specky apm policy`, `specky apm audit`, and `specky apm sbom`.
+- `apm-policy.yml` and `apm.lock.yaml` package governance files. The lock pins SHA256 hashes for packaged primitives and the policy enforces MCP allowlists, allowed hook events, and per-harness tool-name isolation.
+- Harness compiler registry (`src/cli/lib/harness`) and APM governance modules (`src/cli/lib/apm`) with regression coverage.
+
+### Changed
+
+- `npm run build` now checks `apm.yml` name/version parity with `package.json` before compiling.
+- `npm pack --dry-run` now includes `apm.yml`, `apm.lock.yaml`, `apm-policy.yml`, and the compiled `specky apm` command/modules.
+
+## [3.7.2] - 2026-07-06
+
+Platform-native primitive generation for GitHub Copilot and Claude Code.
+
+### Changed
+
+- `.apm` primitive source is now GitHub Copilot-native: agents use VS Code tool ids such as `search`, `agent`, and namespaced Specky MCP tools like `specky/sdd_get_status`; prompts use `agent: agent` frontmatter.
+- `specky install --ide=claude` now transforms the shared source into Claude-native primitives at install time: agents use `Read`, `Glob`, `Grep`, `Task`, and `mcp__specky__sdd_*`; slash commands omit Copilot-only `agent:` metadata; Claude rules use `paths` instead of `applyTo`.
+- `specky install --ide=copilot` keeps Copilot-native syntax in `.github/agents` and `.github/prompts` instead of copying Claude-style tool names.
+
+### Added
+
+- Primitive audit coverage for Copilot-native tool names, namespaced Specky MCP tool ids, and prompt `agent:` frontmatter.
+- Regression tests proving Copilot and Claude installs generate different platform-correct agent, prompt, and instruction frontmatter.
+
+### Fixed
+
+- GitHub Copilot agents no longer receive Claude-only tool names such as `Read`, `Glob`, `Grep`, or `Task`.
+- Claude Code agents no longer receive Copilot-only tool names such as `search`, `agent`, or `specky/sdd_*`.
+
+## [3.7.1] - 2026-07-04
+
+GitHub Copilot primitive metadata and hook cleanup.
+
+### Changed
+
+- Normalized Specky Agent Skill names to lowercase kebab-case matching their folder names.
+- Added agent-mode prompt metadata and corrected reset-phase guidance to use checkpoint restore tools.
+- Reduced native mutating tools in agents where Specky MCP tools perform the artifact writes.
+
+### Fixed
+
+- Copilot instruction file now has `applyTo: '**'` frontmatter.
+- Fixed branch-validator/session hooks to read `current_phase` and string phase names.
+- Prevented Copilot hook manifests from falling back to unresolved Claude plugin paths.
+
 ## [3.7.0] - 2026-07-03
 
 Update awareness: users of old versions now find out — without the server ever
@@ -434,6 +509,7 @@ default array.
 **Regression test (`tests/integration/status-detection.test.ts`):**
 
 4 new tests covering:
+
 1. Greenfield (no `.specs/`) → features:[] + current_phase:init ✅
 2. Single feature in progress → detected with correct phase/progress ✅
 3. Multiple features → aggregated independently with per-feature state ✅

package/README.md

@@ -74,10 +74,10 @@ Specky is a **complete AI development toolkit** — not just an MCP server. The
 
 | Primitive | What it is | Specky includes |
 |-----------|-----------|------------------|
-| **Agents** | Specialized AI personas with defined roles, tools, and guardrails | 13 agents — @specky-orchestrator (full pipeline), @specky-onboarding (wizard), @spec-engineer, @design-architect, @task-planner, @quality-reviewer, and 7 more |
+| **Agents** | Specialized AI personas with defined roles, tools, and guardrails | 13 agents — @specky-orchestrator (full pipeline), @specky-onboarding (wizard), @specky-spec-engineer, @specky-design-architect, @specky-task-planner, @specky-quality-reviewer, and 7 more |
 | **Prompts** | Slash commands that activate the right agent for a task | 22 prompts — `/specky-greenfield`, `/specky-specify`, `/specky-release`, `/specky-orchestrate`, etc. |
 | **Skills** | Domain knowledge files loaded into agent context automatically | 8 skills — SDD pipeline rules, EARS patterns, implementation patterns, test criteria, release gate protocol |
-| **Hooks** | Scripts that run before/after every tool call for validation | 16 hooks — artifact-validator, branch-validator, phase-gate, lgtm-gate, security-scan, etc. |
+| **Hooks** | Scripts that run before/after every tool call for validation | 16 hooks — specky-artifact-validator, specky-branch-validator, specky-phase-gate, specky-lgtm-gate, specky-security-scan, etc. |
 | **MCP Server** | The tool engine that validates, generates, and enforces | 58 tools via Model Context Protocol (the runtime underneath) |
 
 ### Why not just an MCP server?
@@ -97,24 +97,31 @@ Specky ships as a single npm package with a unified `specky` CLI. Works on macOS
 # 1. Install the CLI globally (once per machine)
 npm install -g specky-sdd@latest
 
-# 2. Bootstrap your project — choose your IDE:
+# 2. Bootstrap your project — choose your target harness:
 cd your-project
-specky install --ide=copilot   # VS Code + GitHub Copilot (recommended)
-specky install --ide=claude    # Claude Code
+specky install --target=copilot      # VS Code + GitHub Copilot (recommended)
+specky install --target=claude       # Claude Code
+specky install --target=cursor       # Cursor
+specky install --target=opencode     # OpenCode
+specky install --target=agent-skills # Shared .agents/skills bundle
 ```
 
-> **Important:** Always specify `--ide=copilot` or `--ide=claude`. The default `--ide=auto` installs for both IDEs, which can cause hook cross-read conflicts between Copilot and Claude Code in the same workspace. See [docs/INSTALL.md](docs/INSTALL.md) for details.
+> **Important:** Prefer `--target=...`. The legacy `--ide` flag still works for `copilot`, `claude`, `both`, and `auto`, but it is deprecated in favor of APM-style targets. If Copilot is installed in a workspace, Specky strips Claude hooks from `.claude/settings.json` to prevent Copilot cross-read blocks. See [docs/INSTALL.md](docs/INSTALL.md) for details.
 
 Or per-project (for teams — pins version in `package.json`, run via `npx`):
 
 ```bash
 cd your-project
 npm install --save-dev specky-sdd@latest
-npx specky install --ide=copilot
+npx specky install --target=copilot
 ```
 
 The CLI installs 13 agents, 22 prompts, 8 skills, 16 hooks, the MCP server registration (`.mcp.json` + `.vscode/mcp.json`, pinned to the installed version), and pre-authorizes a **least-privilege** set of tools — the Specky MCP tools plus scoped `git`/`npm`/`npx` and file editing. It does **not** pre-authorize arbitrary shell, `rm`, or network access; those still prompt. Run `specky doctor` anytime to validate integrity and config.
 
+Generated assets are platform-native. `specky install --target=copilot` writes GitHub Copilot agents/prompts with VS Code tool names such as `search`, `agent`, and `specky/sdd_get_status`, plus prompt `agent: agent` frontmatter. `specky install --target=claude` writes Claude Code agents/commands with `Read`, `Glob`, `Grep`, `Task`, and `mcp__specky__sdd_get_status`, with Copilot-only prompt metadata removed. Wave 1 APM targets also include Cursor, OpenCode, and the neutral `agent-skills` target.
+
+Specky also has an APM governance layer for enterprise package control. `apm.yml` declares the package primitives, targets, and MCP runtime; `apm.lock.yaml` pins primitive hashes; `apm-policy.yml` enforces MCP and tool-name policy. Maintainers and CI can run `specky apm validate`, `specky apm policy`, `specky apm verify-lock`, and `specky apm sbom` before publishing or installing. See [Uso do APM pelo Specky](docs/APM-USAGE.md) for the detailed model, including why APM is not a runtime proxy and why users do not need to install the Microsoft APM CLI.
+
 Full walkthroughs per OS, offline install, and CLI reference: [docs/INSTALL.md](docs/INSTALL.md) · [docs/CLI.md](docs/CLI.md).
 
 
@@ -165,15 +172,15 @@ Specky adds a **deterministic engine** between your intent and your code:
 | Any input (PDF, DOCX, PPTX, transcript, Figma) to spec | 58 MCP tools handle all input formats |
 | EARS validation (programmatic, not AI guessing) | 6 patterns enforced at schema level |
 | Enforced pipeline (not suggestions) | 10 phases with actual gates that block advancement |
-| Pre/post hooks on every phase | artifact-validator, branch-validator, phase-gate, lgtm-gate |
+| Pre/post hooks on every phase | specky-artifact-validator, specky-branch-validator, specky-phase-gate, specky-lgtm-gate |
 | 17 diagram types generated automatically | C4 (4 levels), sequence, ER, activity, use case, DFD, deployment, network |
 | Infrastructure as Code | Terraform, Bicep, Dockerfile from DESIGN.md |
 | Work item export | GitHub Issues, Azure Boards, Jira via MCP-to-MCP routing |
 | 6 compliance frameworks | HIPAA, SOC2, GDPR, PCI-DSS, ISO 27001 built-in |
 | Cross-artifact traceability | Requirement to design to task to test to code |
 | Gitflow-SDD branching | spec/NNN → develop → stage → main |
-| Unified CLI distribution | `npm install -g specky-sdd && specky install --ide=copilot` — one binary, multi-OS (macOS/Linux/Windows/WSL) |
-| Works in any MCP host | VS Code + Copilot, Claude Code, Cursor, Windsurf, or any MCP client |
+| Unified CLI distribution | `npm install -g specky-sdd && specky install --target=copilot` — one binary, multi-OS (macOS/Linux/Windows/WSL) |
+| First-class harness targets | VS Code + Copilot, Claude Code, Cursor, OpenCode, plus shared `.agents/skills` |
 | Zero outbound calls from the MCP server | Air-gap friendly; code never leaves your machine. The CLI's once-daily update check is [opt-out](#staying-up-to-date) |
 | MIT open source | Fork it, extend it, audit it. No vendor lock, no seat pricing |
 
@@ -183,7 +190,7 @@ Specky adds a **deterministic engine** between your intent and your code:
 ### Prerequisites
 
 - **Node.js 20+**: [Download here](https://nodejs.org/) (Node 20 LTS recommended)
-- **An AI IDE**: VS Code with Copilot, Claude Code, Cursor, or Windsurf
+- **An AI IDE or agent CLI**: VS Code with Copilot, Claude Code, Cursor, or OpenCode
 
 ### Install the Plugin
 
@@ -880,7 +887,7 @@ Together they form the **SDD layer** of the GitHub + Microsoft enterprise platfo
 }
 ```
 
-> **Note:** This example assumes Specky is installed via `specky install --ide=copilot` (after `npm install -g specky-sdd@latest`). See [Quick Start](#quick-start) for details.
+> **Note:** This example assumes Specky is installed via `specky install --target=copilot` (after `npm install -g specky-sdd@latest`). See [Quick Start](#quick-start) for details.
 
 ## Project Configuration
 
@@ -1026,7 +1033,7 @@ Specky is 100% open source (MIT) — enterprise mode is just an opt-in configura
 - **No `eval()` or dynamic code execution** — template rendering is string replacement only
 - **Path traversal prevention**: FileManager sanitizes all paths, blocks `..` sequences
 - **Zod `.strict()` validation** — every tool input is schema-validated; unknown fields rejected
-- **security-scan hook** blocks commits containing hardcoded secrets (exit code 2)
+- **specky-security-scan hook** blocks commits containing hardcoded secrets (exit code 2)
 - See [SECURITY.md](SECURITY.md) for full OWASP Top 10 coverage
 - See [docs/SYSTEM-DESIGN.md](docs/SYSTEM-DESIGN.md) for complete security architecture
 - See [docs/ENTERPRISE-CONTROLS.md](docs/ENTERPRISE-CONTROLS.md) for RBAC, audit trail, and tool-enforcement controls
@@ -1046,7 +1053,7 @@ When using Specky, follow these practices to protect your data:
 | **Protect the `.specs/` directory** | Contains your specification artifacts (architecture, API contracts, business logic) | Add `.specs/` to `.gitignore` if specs contain sensitive IP, or use a private repo |
 | **Protect checkpoints** | `.specs/{feature}/.checkpoints/` stores full artifact snapshots | Same as above — treat checkpoints like source code |
 | **Review auto-generated specs before committing** | Turnkey and auto-pipeline generate from natural language — may capture sensitive details | Review SPECIFICATION.md and DESIGN.md before `git add` |
-| **Keep the security-scan hook enabled** | Detects API keys, passwords, tokens in staged files | Comes pre-configured; don't disable `.claude/hooks/security-scan.sh` |
+| **Keep the specky-security-scan hook enabled** | Detects API keys, passwords, tokens in staged files | Comes pre-configured; don't disable `.claude/hooks/specky-security-scan.sh` |
 | **Use environment variables for secrets** | Specky never stores credentials, but your specs might reference them | Write `$DATABASE_URL` in specs, never the actual connection string |
 | **Run `npm audit` regularly** | Catches dependency vulnerabilities | `npm audit` — CI runs this automatically on every PR |
 
@@ -1116,9 +1123,9 @@ npm run dev
 echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | node dist/index.js 2>/dev/null
 
 # Run the published image from GHCR (multi-arch: linux/amd64 + linux/arm64)
-docker pull ghcr.io/paulasilvatech/specky:latest        # or pin a release: :3.6.0
+docker pull ghcr.io/paulasilvatech/specky:latest        # or pin a release: :3.8.0
 docker run --rm -p 3200:3200 ghcr.io/paulasilvatech/specky:latest
-curl http://localhost:3200/health                       # -> {"status":"ok","version":"3.6.0"}
+curl http://localhost:3200/health                       # -> {"status":"ok","version":"3.8.0"}
 
 # Or build and run locally from source
 docker build -t specky-sdd:dev .
@@ -1140,7 +1147,7 @@ deployments (enterprise profile, token auth, TLS proxy, private packages) see
 |------------|--------|
 | 58 MCP tools across 10 enforced pipeline phases | Stable |
 | Unified `specky` CLI: install, doctor, status, upgrade, hooks, serve | Stable |
-| IDE-specific install: `--ide=copilot` or `--ide=claude` | Stable |
+| Target-specific install: `--target=copilot`, `claude`, `cursor`, `opencode`, or `agent-skills` | Stable |
 | Copilot-safe hook manifests (no lifecycle event cross-read) | Stable |
 | Phase validation on every tool with gate enforcement | Stable |
 | 17 software engineering diagram types (C4, sequence, ER, DFD, deployment, network) | Stable |

package/apm-policy.yml

@@ -0,0 +1,53 @@
+# apm-policy.yml — enterprise governance policy for Specky primitive packaging.
+#
+# Enforced by `specky apm policy check` (and in CI via .github/workflows).
+# The goal is least-privilege, reproducible, harness-isolated primitives.
+
+schemaVersion: 1
+
+# Package sources that may be installed/trusted.
+allowedSources:
+  - github.com/paulasilvatech/specky
+  - registry.npmjs.org/specky-sdd
+
+# MCP governance. Only these servers may be declared in apm.yml, and
+# transitive MCP servers are not auto-trusted.
+mcp:
+  allowTransitive: false
+  allowedServers:
+    - specky
+
+# Hook governance. Hook manifests may only register these event types.
+hooks:
+  allowedEvents:
+    - SessionStart
+    - UserPromptSubmit
+    - PreToolUse
+    - PostToolUse
+    - Stop
+
+# Per-target tool-name isolation. Compiled output for one harness must never
+# contain another harness's native tool tokens.
+targets:
+  github-copilot:
+    forbidToolTokens:
+      - Read
+      - Glob
+      - Grep
+      - Task
+      - mcp__specky__
+  claude-code:
+    forbidToolTokens:
+      - "specky/"
+  cursor:
+    forbidToolTokens:
+      - "specky/"
+      - '"search"'
+      - '"agent"'
+  opencode:
+    forbidToolTokens:
+      - Read
+      - Glob
+      - Grep
+      - Task
+      - mcp__specky__