ma-agents 3.6.2 → 3.8.0

package/AGENTS.md

@@ -1,97 +0,0 @@
-<!-- Generated by ma-agents. Edit outside the MA-AGENTS-START/END markers to preserve your changes. -->
-# Project Agent Instructions
-
-This file is auto-discovered by OpenCode and any agent that respects `AGENTS.md`.
-It establishes universal safety rules, text-vs-file discipline, and BMAD phase
-discipline for every agent operating in this project.
-
-## Universal Rules
-
-The universal rules block below is stamped and maintained by ma-agents. Edit
-outside the HTML-comment `MA-AGENTS` start and end markers to preserve your
-own additions — content inside the markers is regenerated on every install.
-
-<!-- MA-AGENTS-START -->
-# AI Agent Skills - Planning Instruction
-
-You have access to a library of skills in your skills directory. Before starting any task:
-
-1. Read the skill manifest at .opencode/skills/MANIFEST.yaml
-2. Based on the task description, select which skills are relevant
-3. Read only the selected skill files
-4. Then proceed with the task
-
-Always load skills marked with always_load: true.
-Do not load skills that are not relevant to the current task.
-
-## Respond in TEXT vs. create FILES
-
-Choose your response medium deliberately. Defaulting to file creation when the user asked a question is a common failure mode — especially for coding agents running in web UIs.
-
-- **Create or modify FILES when the user's request contains file-action keywords:** `create`, `write`, `generate`, `build`, `implement` (and obvious synonyms such as `add`, `produce`, `refactor`, `fix`, `update <file>`). These signal a concrete artifact is expected.
-- **Respond in TEXT when the request contains text-response keywords:** `what do you think`, `how should we`, `discuss`, `opinion` (and obvious synonyms such as `explain`, `why`, `should I`, `compare`, `recommend`). These signal that a conversation is expected, not a deliverable.
-- **If unsure, respond in TEXT.** A text answer can always be followed by file creation on confirmation; an unwanted file cannot be cleanly undone.
-- **Never create `response.md`, `output.md`, or any similarly named scratch file as a reply.** A reply belongs in the chat transcript, not on disk.
-- **Confirm file paths before writing.** When you are about to create or modify a file whose path the user has not explicitly named, state the intended path in text and wait for confirmation, unless the path is unambiguous from the task context.
-
-## BMAD phase discipline
-
-BMAD-METHOD organizes work into declared phases (analysis, planning, architecture, story-creation, implementation, review). Respect the currently declared phase.
-
-- **Do not skip ahead to implementation during planning.** If the project is in a planning phase — or the user has asked for requirements, architecture, or a story — produce planning artifacts, not code.
-- **Do not retroactively plan after you have already coded.** If implementation has already started, flag the gap instead of fabricating back-dated planning documents.
-- The declared phase is established by the active skill, the story status, or an explicit statement from the user. When none of these is available, ask before assuming.
-<!-- MA-AGENTS-END -->
-
-## Critical Behavior Rules
-
-These rules are non-negotiable across every profile and every agent.
-
-- **Never create files in `~/.claude/` or any user home directory.** All
-  project artifacts must land inside the current working directory. Home-
-  directory writes cross-contaminate between projects and are a common source
-  of secret/config leakage.
-- **Never write outside the project root without an explicit user request
-  naming the absolute path.** "Write to disk" means the project, not the
-  operator's machine.
-- **Do not modify files you did not read first.** Read the current content
-  before proposing or performing an edit — blind writes silently destroy user
-  work.
-
-## BMAD Phase Declaration
-
-BMAD-METHOD organizes work into four phases. Respect the currently declared
-phase; do not skip ahead to the next phase without a phase transition signal
-from the user, the active skill, or the story status.
-
-- **Discovery / PM (analysis, planning).** Deliverables: product briefs,
-  PRDs, market and domain research, epics and stories lists. Do NOT produce
-  code, architecture diagrams, or implementation artifacts in this phase.
-  When asked "what do you think", respond in text.
-- **Architecture.** Deliverables: solution design, component boundaries,
-  data-flow, interface contracts. Do NOT write application code or skill
-  implementations. Narrate decisions and capture them as documents.
-- **Tech Lead / Stories.** Deliverables: individual story files with full
-  acceptance criteria, task breakdowns, and dev notes. Do NOT begin
-  implementation — stories are contracts the implementer consumes later.
-- **Implementation.** Deliverables: code, tests, and the Dev Agent Record on
-  the story file. At this phase, write files. Do NOT retroactively fabricate
-  planning documents for code that already exists — flag the gap instead.
-
-When no phase is declared (no active skill, no story in progress, no explicit
-user statement), ask before assuming.
-
-## Project BMAD Output Structure
-
-BMAD artifacts live under `_bmad-output/` (or the paths configured in
-`_bmad/bmm/config.yaml` when present). The install-time resolver logs the
-resolved paths on each run; consult that log output if in doubt.
-
-- **Planning artifacts** — PRDs, product briefs, market and domain research.
-- **Architecture artifacts** — solution design, component boundaries. May be
-  co-located with planning artifacts when no separate directory is configured.
-- **Implementation artifacts (stories)** — individual story files and their
-  Dev Agent Records.
-
-Always consult the `MANIFEST.yaml` referenced inside the universal block above
-for the full list of installed skills and their locations.

package/AiAudit.md

@@ -1,12 +0,0 @@
-# AI Audit Trail
-
-| Date | Task | Tokens (est.) |
-|------|------|---------------|
-| 2026-03-18 | Story 9.2: JSON Injection — Create opencode.json When Absent. Added MA_AGENTS_SOURCE constant, json-merge branch in updateAgentInstructions(), and 12-test fixture suite. | In: ~18K / Out: ~6K |
-| 2026-04-06 | Story 17.11: Rework add-to-sprint skill with unified sprint-status.yaml movement semantics. Created IDE skill (skills/add-to-sprint/), rewrote BMAD extension skill and workflow, updated module-help.csv. Full develop + code review + PR cycle. | In: ~35K / Out: ~12K |
-| 2026-04-06 | Story 17.12: Rework remove-from-sprint skill with unified sprint-status.yaml reverse movement semantics. Created IDE skill, BMAD extension skill, workflow wrapper, module-help.csv row. Full develop + code review cycle. PR #17. | In: ~30K / Out: ~14K |
-| 2026-04-06 | Story 17.13: Rework sprint-status-view skill for unified sprint-status.yaml three-section schema. Created IDE skill (skills/sprint-status-view/), rewrote BMAD SKILL.md and workflow.md, updated module-help.csv. Full develop + code review + fix cycle. PR #18. | In: ~40K / Out: ~16K |
-| 2026-04-06 | Story 17.14: Create cleanup-done skill from scratch (greenfield). IDE skill + BMAD extension with 9-step archival workflow for unified schema. Full develop + code review + fix cycle. PR #19. | In: ~35K / Out: ~14K |
-| 2026-04-06 | Story 17.18: Rework bmad-dev-story as BMAD extension override. Replaced flat development_status map operations with cross-section item search on unified sprint-status.yaml schema. Full develop + code review + fix cycle. PR #21. | In: ~25K / Out: ~12K |
-| 2026-04-06 | Story 17.20: Rework bmad-sprint-status skill as BMAD extension override + IDE skill for unified sprint-status.yaml schema. Analysis-focused health summary with 10 risk conditions, backlog health, epic progress, sprint history, 3 execution modes. Full develop + code review + PR cycle. PR #23. | In: ~30K / Out: ~15K |
-| 2026-04-06 | Story 17.22: Jira Adapter Pattern — design specification story. Created adapter-pattern-spec.md (8 sections: detection logic, interface contract, skill template, skill mapping, Jira requirements, pipeline integration, extensibility). Full develop + code review + fix cycle. PR #26. | In: ~20K / Out: ~10K |

package/DEVELOPMENT.md

@@ -1,173 +0,0 @@
-# Development Guide
-
-Guidelines for contributing to ma-agents — for both AI agents and human developers.
-
-## Setup
-
-```bash
-git clone https://github.com/mayafit/AI_Agents.git
-cd AI_Agents
-npm install
-node bin/cli.js help
-```
-
-## Project Architecture
-
-```
-ma-agents/
-├── bin/cli.js              CLI entry point (wizard, commands, flag parsing)
-├── lib/
-│   ├── agents.js           Agent configurations (paths, versions, resource maps)
-│   └── installer.js        Core logic (install, uninstall, manifest, status)
-├── skills/                 Bundled skills (one directory per skill)
-├── index.js                Programmatic API exports
-├── SKILLS_STRUCTURE.md     Skill authoring reference
-├── DEVELOPMENT.md          This file
-└── package.json
-```
-
-## Versioning (Semver)
-
-This project tracks three independent version numbers. All follow [Semantic Versioning](https://semver.org/).
-
-### Package Version (`package.json`)
-
-The npm package version. Bump on every publish.
-
-| Change | Bump | Example |
-|--------|------|---------|
-| Bug fix, typo in CLI | PATCH | 1.4.0 → 1.4.1 |
-| New command, new feature | MINOR | 1.4.0 → 1.5.0 |
-| Breaking API change | MAJOR | 1.4.0 → 2.0.0 |
-
-### Skill Version (`skills/<name>/skill.json`)
-
-Each skill has its own version. Bump when skill content changes.
-
-| Change | Bump | Example |
-|--------|------|---------|
-| Typo fix, minor wording | PATCH | 1.0.0 → 1.0.1 |
-| New instructions, new resources added | MINOR | 1.0.0 → 1.1.0 |
-| Breaking changes to skill behavior or structure | MAJOR | 1.0.0 → 2.0.0 |
-
-When you bump a skill version, the installer will detect the change and offer users an upgrade.
-
-### Agent Version (`lib/agents.js`)
-
-Each agent configuration has a version. Bump when the agent config changes.
-
-| Change | Bump | Example |
-|--------|------|---------|
-| Description update, path correction | PATCH | 1.0.0 → 1.0.1 |
-| New field added (e.g., resourceMap) | MINOR | 1.0.0 → 1.1.0 |
-| Path structure change that breaks existing installs | MAJOR | 1.0.0 → 2.0.0 |
-
-## Adding a New Skill
-
-1. Create the directory: `mkdir -p skills/my-skill`
-2. Create `skill.json` with `name`, `description`, `version` (start at `1.0.0`)
-3. Create `SKILL.md` — pure Markdown, no YAML frontmatter
-4. (Optional) Add `scripts/`, `references/`, `examples/`, `hooks/`, `assets/`
-5. (Optional) Create agent-specific templates: `claude-code.md`, `cline.md`, `generic.md`
-6. Verify: `node bin/cli.js list` — your skill should appear
-7. Test install: `node bin/cli.js install my-skill claude-code`
-8. Check the installed output in `.claude/skills/my-skill/SKILL.md`
-
-See [SKILLS_STRUCTURE.md](SKILLS_STRUCTURE.md) for full documentation.
-
-## Adding a New Agent
-
-1. Edit `lib/agents.js`
-2. Add a new entry to the `agents` array with all required fields:
-   - `id` — unique kebab-case identifier
-   - `name` — display name
-   - `version` — start at `1.0.0`
-   - `description` — brief description
-   - `getProjectPath()` — returns project-level skills path
-   - `getGlobalPath()` — returns global path (handle win32, darwin, linux)
-   - `fileExtension` — usually `.md`
-   - `template` — template ID (`generic`, `claude-code`, `cline`, or new)
-   - `resourceMap` — (optional) rename directories for this agent
-3. Test: `node bin/cli.js agents` — your agent should appear
-4. Test install: `node bin/cli.js install code-review my-agent`
-
-## Manifest System
-
-The installer writes `.ma-agents.json` into each agent's install directory to track what's installed. This enables upgrade detection, version comparison, and clean uninstalls.
-
-```json
-{
-  "manifestVersion": "1.0.0",
-  "agent": "claude-code",
-  "scope": "project",
-  "skills": {
-    "code-review": {
-      "version": "1.0.0",
-      "installedAt": "2026-02-17T12:34:56Z",
-      "updatedAt": "2026-02-17T12:34:56Z",
-      "installerVersion": "1.4.0",
-      "agentVersion": "1.0.0"
-    }
-  }
-}
-```
-
-Do not edit manifests manually. Use `npx ma-agents status` to view and `npx ma-agents uninstall` to remove.
-
-## Pre-Publish Checklist
-
-Before running `npm publish`:
-
-- [ ] Package version bumped in `package.json`
-- [ ] Skill versions bumped for any changed skills
-- [ ] Agent versions bumped for any changed agent configs
-- [ ] `node bin/cli.js list` — all skills appear
-- [ ] `node bin/cli.js agents` — all agents appear
-- [ ] Test fresh install: `node bin/cli.js install code-review claude-code --force`
-- [ ] Test upgrade detection: run install again without `--force`
-- [ ] Test uninstall: `node bin/cli.js uninstall code-review claude-code`
-- [ ] Test status: `node bin/cli.js status`
-- [ ] `node bin/cli.js help` — help text is up to date
-- [ ] Commit with conventional commit message
-
-## Commit Conventions
-
-Use [Conventional Commits](https://www.conventionalcommits.org/):
-
-```
-feat: add new skill for API testing
-fix: correct Cline resource mapping for docs/
-chore: bump code-review skill to v1.0.1
-docs: update SKILLS_STRUCTURE.md with hooks directory
-refactor: extract manifest logic into separate module
-```
-
-**Scopes** (optional): `cli`, `installer`, `agents`, `skills`, `docs`
-
-```
-feat(cli): add status command
-fix(installer): handle missing manifest gracefully
-feat(skills): add vercel-react-best-practices skill
-```
-
-## Testing Locally
-
-```bash
-# Run CLI directly
-node bin/cli.js
-
-# Test specific commands
-node bin/cli.js list
-node bin/cli.js agents
-node bin/cli.js status
-node bin/cli.js help
-
-# Test install flow
-node bin/cli.js install code-review claude-code --force
-node bin/cli.js status
-node bin/cli.js uninstall code-review claude-code
-node bin/cli.js status
-
-# Quick smoke test (programmatic)
-node -e "const m = require('.'); console.log('Skills:', m.listSkills().length, 'Agents:', m.listAgents().length)"
-```

package/MANIFEST.yaml

@@ -1,3 +0,0 @@
-# MANIFEST.yaml
-
-skills:

package/_bmad-output/implementation-artifacts/16-4-validation-report.md

@@ -1,79 +0,0 @@
-# Story 16.4 Validation Report: Cross-Repo Path Resolution
-
-Generated: 2026-03-28
-
-## Audit Summary
-
-**Result: PASS** - All BMAD workflows are 100% config-driven. No hardcoded `_bmad-output/` paths found.
-
-## Gap Analysis Table
-
-| Workflow | Phase | Path Source | Hardcoded? | Config Key Used | Change Needed |
-|----------|-------|-----------|-----------|----------------|---------------|
-| bmad-product-brief | 1-Analysis | config.yaml | No | planning_artifacts | None |
-| bmad-domain-research | 1-Analysis | config.yaml | No | planning_artifacts | None |
-| bmad-market-research | 1-Analysis | config.yaml | No | planning_artifacts | None |
-| bmad-technical-research | 1-Analysis | config.yaml | No | planning_artifacts | None |
-| bmad-create-prd | 2-Planning | config.yaml | No | planning_artifacts | None |
-| bmad-create-ux-design | 2-Planning | config.yaml | No | planning_artifacts | None |
-| bmad-validate-prd | 2-Planning | config.yaml | No | planning_artifacts | None |
-| bmad-edit-prd | 2-Planning | config.yaml | No | planning_artifacts | None |
-| bmad-create-architecture | 3-Solutioning | config.yaml | No | planning_artifacts | None |
-| bmad-create-epics-and-stories | 3-Solutioning | config.yaml | No | planning_artifacts | None |
-| bmad-check-implementation-readiness | 3-Solutioning | config.yaml | No | planning_artifacts | None |
-| bmad-generate-project-context | 3-Solutioning | config.yaml | No | planning_artifacts | None |
-| bmad-sprint-planning | 4-Implementation | config.yaml | No | implementation_artifacts, planning_artifacts | None |
-| bmad-sprint-status | 4-Implementation | config.yaml | No | implementation_artifacts | None |
-| bmad-create-story | 4-Implementation | config.yaml | No | implementation_artifacts, planning_artifacts | None |
-| bmad-dev-story | 4-Implementation | config.yaml | No | implementation_artifacts | None |
-| bmad-retrospective | 4-Implementation | config.yaml | No | implementation_artifacts | None |
-| bmad-code-review | 4-Implementation | config.yaml | No | planning_artifacts, implementation_artifacts | None |
-| bmad-correct-course | 4-Implementation | config.yaml | No | implementation_artifacts | None |
-| bmad-quick-dev | 4-Implementation | config.yaml | No | implementation_artifacts, planning_artifacts | None |
-| bmad-qa-generate-e2e-tests | 4-Implementation | config.yaml | No | implementation_artifacts | None |
-
-## Config Resolution Chain
-
-All workflows follow this identical pattern:
-1. Load config from `{project-root}/_bmad/bmm/config.yaml`
-2. Resolve `planning_artifacts` and `implementation_artifacts` from config values
-3. Use `{planning_artifacts}/...` and `{implementation_artifacts}/...` for all path references
-
-**Multi-repo resolution:**
-- `planning_artifacts` = `{knowledgebase_path}/_bmad-output/planning-artifacts`
-- `implementation_artifacts` = `{sprint_management_path}/_bmad-output/implementation-artifacts`
-
-**Single-repo resolution (backward compatible):**
-- `planning_artifacts` = `_bmad-output/planning-artifacts`
-- `implementation_artifacts` = `_bmad-output/implementation-artifacts`
-
-## Source-of-Truth Precedence
-
-| File | Role | Authority |
-|------|------|-----------|
-| `_bmad/bmm/config.yaml` | Runtime source of truth | PRIMARY |
-| `_bmad-output/project-layout.yaml` | Agent discovery file | INFORMATIONAL |
-| `_bmad-output/project-context.md` | Agent constitutional doc | INSTRUCTIONAL |
-
-If these disagree, `_bmad/bmm/config.yaml` wins.
-
-## Backward Compatibility (NFR34)
-
-Single-repo mode writes:
-- `knowledgebase_path: "."` and `sprint_management_path: "."`
-- `planning_artifacts: "_bmad-output/planning-artifacts"`
-- `implementation_artifacts: "_bmad-output/implementation-artifacts"`
-
-These values are identical to the pre-Epic-16 default behavior. No workflow changes needed.
-
-## Path Accessibility
-
-Story 16.1 validates external paths at wizard time:
-- `fs.existsSync()` checks for local paths
-- `fs.statSync().isDirectory()` confirms it's a directory
-- Git clone validates remote paths
-- Non-existent paths generate warnings
-
-## Conclusion
-
-**No backlog items needed.** All 21 BMAD workflows already support config-driven path resolution through the `planning_artifacts` and `implementation_artifacts` config keys. Story 16.2's config write (updated during 16.4 validation) now also writes these derived fields, completing the end-to-end resolution chain.

package/_bmad-output/implementation-artifacts/17-10-rework-generate-backlog.md

@@ -1,237 +0,0 @@
-# Story 17.10: Rework generate-backlog Skill (Heavy Rework)
-
-Status: review
-
-## Story
-
-As a **Scrum Master**,
-I want the `generate-backlog` skill to populate the `backlog` section of the unified `sprint-status.yaml`,
-So that all unassigned stories and bugs are maintained in a single file rather than a separate `backlog.yaml`.
-
-## Acceptance Criteria
-
-1. **Given** the `generate-backlog` skill is invoked from ANY IDE agent (Claude Code, Cursor, Cline, Roo Code, Gemini, Copilot, Kilocode, etc.) OR from a BMAD workflow,
-   **When** it parses the epics document and bug files,
-   **Then** it writes all unassigned stories and bugs to the `backlog` section of `sprint-status.yaml` in priority order,
-   **And** it updates the `epics` section with current epic metadata (status, retrospective),
-   **And** it does NOT touch the `sprints` section -- sprint-assigned items are preserved.
-
-2. **Given** items already exist in the `sprints` section of `sprint-status.yaml`,
-   **When** the backlog is regenerated,
-   **Then** items currently assigned to any sprint are NOT duplicated in the `backlog` section (single-location invariant),
-   **And** new stories from `epics.md` that don't exist anywhere in `sprint-status.yaml` are added to `backlog`.
-
-3. **Given** a story exists in `backlog` but has been removed from `epics.md`,
-   **When** the backlog is regenerated,
-   **Then** the orphaned item is flagged with a warning but NOT automatically removed (human review required).
-
-4. **Given** bugs exist as standalone story files (FR64),
-   **When** the backlog is regenerated,
-   **Then** bugs are included in the `backlog` section with `type: bug` and `epic: null`,
-   **And** bug-specific fields (`severity`) are preserved.
-
-5. **Given** items have been archived in the `done/` folder,
-   **When** the backlog is regenerated,
-   **Then** archived items are NOT reintroduced into the `backlog` section.
-
-6. **Given** the skill source files exist in BOTH deployment pipelines (IDE skill + BMAD extension),
-   **When** the ma-agents installer is run,
-   **Then** the IDE skill is deployed to all agent directories via `lib/installer.js` (`performInstall`),
-   **And** the BMAD extension skill is deployed via `lib/bmad.js` to `_bmad/extensions/`,
-   **And** the installed copies are byte-identical to their source (minus frontmatter injection by the installer).
-
-## Tasks / Subtasks
-
-### Task 1: Create the IDE skill source files (AC: 1, 6)
-
-- [x] 1.1 Create `skills/generate-backlog/skill.json` with metadata:
-  ```json
-  {
-    "name": "generate-backlog",
-    "version": "1.0.0",
-    "description": "Generate or refresh the backlog section of sprint-status.yaml from epics and bug stories, preserving existing priorities and sprint assignments",
-    "category": "workflow",
-    "tags": ["backlog", "sprint-management", "epics", "bugs"]
-  }
-  ```
-  Note: `always_load` is intentionally omitted (defaults to false) -- this skill is invoked on demand, not loaded for every task.
-
-- [x] 1.2 Create `skills/generate-backlog/SKILL.md` with the complete skill workflow (see Task 3 for content specification). This is the canonical skill content that the installer deploys to all IDE agents.
-
-### Task 2: Create the BMAD extension skill source files (AC: 1, 6)
-
-- [x] 2.1 Create `lib/bmad-extension/skills/generate-backlog/SKILL.md` -- this is a SEPARATE file from the IDE skill SKILL.md. The BMAD extension version is authored for the BMAD Scrum Master agent (`bmm-sm`) context and may have BMAD-specific phrasing (e.g., referencing `_bmad/bmm/config.yaml` for path resolution). The core workflow logic MUST be functionally identical to the IDE version.
-
-- [x] 2.2 Create `lib/bmad-extension/skills/generate-backlog/bmad-skill-manifest.yaml`:
-  ```yaml
-  type: skill
-  name: generate-backlog
-  module: ma-skills
-  ```
-
-- [x] 2.3 Register the skill in `lib/bmad-extension/module-help.csv` by adding a row:
-  ```csv
-  ma-skills,4-implementation,Generate Backlog,generate-backlog,,skill:generate-backlog,generate-backlog,false,bmm-sm,,"Generate or refresh the backlog section of sprint-status.yaml from epics and bug stories.",_bmad-output/implementation-artifacts,"backlog",
-  ```
-  The `agent` column is `bmm-sm` (Scrum Master) because backlog generation is a Scrum Master responsibility.
-
-### Task 3: Implement the skill workflow content (AC: 1, 2, 3, 4, 5)
-
-The SKILL.md content (for both the IDE and BMAD extension versions) must implement the following workflow:
-
-- [x] 3.1 **Step 1 -- Load existing state:** Read `sprint-status.yaml` (if it exists). Parse the `sprints` section to build a set of all item IDs already assigned to sprints (`sprint_item_ids`). Parse the `backlog` section for existing items (to preserve priorities during merge). Scan the `done/` folder to build a set of archived item IDs (`done_item_ids`). If `sprint-status.yaml` does not exist, report an error and suggest running `bmad-sprint-planning` first.
-
-- [x] 3.2 **Step 2 -- Extract stories from epics.md:** Parse `epics.md` to extract all epics and their stories. For each story, generate the kebab-case item ID (`N-M-title-slug`). Exclude items in `sprint_item_ids` (already in a sprint). Exclude items in `done_item_ids` (archived).
-
-- [x] 3.3 **Step 3 -- Extract bugs:** Glob for `bug-*.md` files in the implementation artifacts directory. Parse YAML frontmatter for title, severity, status. Create bug items with `type: bug`, `epic: null`, `severity` from frontmatter. Exclude bugs in `sprint_item_ids` or `done_item_ids`.
-
-- [x] 3.4 **Step 4 -- Merge with existing backlog:** For items already in the existing `backlog` section, preserve their `priority` and `status` values. For items in existing backlog whose IDs do NOT appear in `epics.md` or bug files, flag as orphaned with a WARNING but keep them in the backlog (do not auto-remove). For newly discovered items (not in existing backlog, not in sprints, not in done), add with `status: backlog`.
-
-- [x] 3.5 **Step 5 -- Priority ordering:** Sort all backlog items: critical bugs first, then by explicit priority (preserved from existing backlog), then by epic order. Re-number priorities sequentially 1..N to match array position.
-
-- [x] 3.6 **Step 6 -- Build epics section:** Rebuild the `epics` section from parsed epics in `epics.md`. Preserve existing `status` and `retrospective` values for epics already in the file (never downgrade). Add new epics with `status: backlog`, `retrospective: optional`.
-
-- [x] 3.7 **Step 7 -- Write sprint-status.yaml:** Assemble the complete file: preserve top-level metadata (`generated`, `project`, `project_key`, `tracking_system`, `story_location`), update `last_updated` timestamp, write refreshed `epics` section, write refreshed `backlog` section, preserve `sprints` section UNCHANGED. Single atomic write (read-modify-write pattern).
-
-- [x] 3.8 **Step 8 -- Report summary:** Output summary with counts: total stories, total bugs, new items added, orphaned items flagged, items excluded (sprint-assigned), items excluded (archived in done/).
-
-### Task 4: Verify the old `backlog.yaml` standalone write is NOT present (AC: 1)
-
-- [x] 4.1 Confirm neither SKILL.md file contains any instruction to write a standalone `backlog.yaml` file.
-- [x] 4.2 Confirm the only write target is `sprint-status.yaml`.
-- [x] 4.3 If the previous (rolled-back) implementation left any references to `backlog.yaml` as an output, remove them.
-
-### Task 5: Deployment verification (AC: 6)
-
-- [x] 5.1 Run `npx ma-agents` (or `node bin/cli.js`) to trigger the installer.
-- [x] 5.2 Verify the IDE skill appears in the installed MANIFEST.yaml for at least one agent (e.g., check `.claude/skills/MANIFEST.yaml` includes `generate-backlog`).
-- [x] 5.3 Diff the installed IDE copy (e.g., `.claude/skills/generate-backlog/SKILL.md`) against the source (`skills/generate-backlog/SKILL.md`) -- the content should match after accounting for frontmatter injection by the installer.
-- [x] 5.4 BMAD extension source files confirmed at `lib/bmad-extension/skills/generate-backlog/`; deployed to `_bmad/extensions/ma-agents-skills/` during full BMAD agent install via `lib/bmad.js` `STAGE:EXTENSION` logic.
-- [x] 5.5 `generate-backlog` registered in `lib/bmad-extension/module-help.csv` for `bmm-sm` agent.
-
-## Dev Notes
-
-### CRITICAL: Two Deployment Pipelines (Read This First)
-
-The ma-agents project is a **multi-agent skill installer** that deploys skills to 8+ IDE coding agents. There are TWO independent deployment pipelines, and this story creates source files for BOTH.
-
-**Why this matters:** The previous version of this story was fundamentally wrong -- it directed edits to `.claude/skills/generate-backlog/SKILL.md`, which is an INSTALLED COPY (read-only deployed artifact). That path is where the installer OUTPUTS files, not where source files live.
-
-#### Pipeline 1: IDE Skills (all IDE agents)
-- **Source location:** `skills/generate-backlog/skill.json` + `skills/generate-backlog/SKILL.md`
-- **Deployed by:** `lib/installer.js` -> `performInstall()` which:
-  1. Reads `skill.json` for metadata
-  2. Falls back through: `templates/<agent>.md` -> `templates/generic.md` -> `SKILL.md`
-  3. Strips existing frontmatter, injects fresh frontmatter from `skill.json`
-  4. Copies to each agent's install directory (e.g., `.claude/skills/`, `.cursor/skills/`, etc.)
-- **Never hardcode agent paths.** The installer handles deployment to all agents automatically.
-- **Reference skill:** See `skills/story-status-lookup/` for a working example of `skill.json` + `SKILL.md`.
-
-#### Pipeline 2: BMAD Extension Skills (BMAD agents only)
-- **Source location:** `lib/bmad-extension/skills/generate-backlog/SKILL.md` + `bmad-skill-manifest.yaml`
-- **Deployed by:** `lib/bmad.js` which copies `lib/bmad-extension/` to `_bmad/extensions/ma-agents-skills/`
-- **Registered in:** `lib/bmad-extension/module-help.csv` (maps skill to `bmm-sm` agent)
-- **Reference skill:** See `lib/bmad-extension/skills/add-to-sprint/` for a working example of `SKILL.md` + `bmad-skill-manifest.yaml`.
-
-#### Install locations (NEVER edit these directly)
-- `.claude/skills/`, `.cursor/skills/`, `.cline/skills/`, `.roo/skills/`, `.gemini/skills/`, `.github/copilot/skills/`, `.kilocode/skills/` -- all managed by installer
-- `_bmad/extensions/ma-agents-skills/skills/` -- managed by BMAD deployer
-
-### What This Story Changes vs Current Behavior
-
-**Current state:** The `generate-backlog` skill does NOT currently exist in either pipeline. The previous (rolled-back) implementation only modified an installed copy at `.claude/skills/generate-backlog/SKILL.md`, which would have been overwritten on the next install. This story creates the skill from scratch in both source locations.
-
-**New behavior:** The skill reads `epics.md` and `bug-*.md` files, then writes the `backlog` and `epics` sections of `sprint-status.yaml`. The `sprints` section is preserved unchanged. Items in sprints or in the `done/` archive are excluded. Orphaned items are flagged but kept.
-
-### Key Design Decisions
-
-- **Output target:** `sprint-status.yaml` `backlog` + `epics` sections (NOT a standalone `backlog.yaml`)
-- **Sprint-assigned item exclusion:** Must read `sprints` section to build exclusion set (single-location invariant from Story 17.9)
-- **Done exclusion:** Scans `done/` folder to prevent reintroducing archived items
-- **Orphan detection:** Items in existing backlog that no longer appear in source files get a warning but are NOT removed
-- **Atomic write:** Single read-modify-write to `sprint-status.yaml`; `sprints` section passed through unchanged
-- **Priority sort:** Critical bugs > explicit priority (preserved) > epic order; renumbered 1..N
-- **No `sprint` field on backlog items:** Sprint assignment is structural in the unified model (items in a sprint's `items` array are "assigned")
-
-### Unified Schema Sections Touched
-
-- **`backlog`** -- primary write target (full replacement of items not in sprints or done)
-- **`epics`** -- updated with refreshed epic metadata from epics.md
-- **`sprints`** -- read-only (used to build the exclusion set; preserved unchanged on write)
-
-### Reference Files
-
-- **Schema:** `_bmad-output/planning-artifacts/sprint-status-schema.md` (canonical schema for sprint-status.yaml)
-- **Epics source:** `_bmad-output/planning-artifacts/epics.md`
-- **Bug files:** `_bmad-output/implementation-artifacts/bug-*.md`
-- **Done archive:** `_bmad-output/implementation-artifacts/done/`
-- **Sprint status:** `_bmad-output/implementation-artifacts/sprint-status.yaml`
-- **IDE skill reference:** `skills/story-status-lookup/skill.json` + `skills/story-status-lookup/SKILL.md`
-- **BMAD skill reference:** `lib/bmad-extension/skills/add-to-sprint/` (SKILL.md + bmad-skill-manifest.yaml)
-- **Module help CSV:** `lib/bmad-extension/module-help.csv`
-
-### Cross-References
-
-- **Story 17.9** (prerequisite): Defines the unified `sprint-status.yaml` schema this skill writes to
-- **Story 17.15** (prerequisite): `bmad-sprint-planning` bootstraps the file; `generate-backlog` refreshes the backlog section on subsequent runs
-- **Story 17.11** (downstream): `add-to-sprint` moves items from the backlog section this skill populates into sprints
-- **Story 17.24** (downstream): `prioritize-backlog` reorders items in the backlog section this skill populates
-- **Story 17.23** (future): Migration story that deprecates the old standalone `backlog.yaml` file
-
-### PRD Traceability
-
-- **FR64:** Bugs exist in the backlog as standalone items -- never assigned to an epic
-- **FR133:** `sprint-status.yaml` includes top-level metadata (generated, last_updated, project, etc.)
-- **FR134:** Each item carries consistent structure (id, type, epic, title, priority, status, severity)
-- **FR67:** Prioritization supports multiple criteria beyond epic precedence
-
-### Architecture Reference
-
-- Architecture Decision P2-11 in `_bmad-output/planning-artifacts/architecture.md`
-
-## Dev Agent Record
-
-### Implementation Notes
-
-- All task files created from scratch — no previous implementation existed in either pipeline (previous agent had only modified installed copies, which were rolled back).
-- IDE skill deployed via `node bin/cli.js install generate-backlog claude-code` — confirmed installed to `.claude/skills/generate-backlog/` with content matching source (frontmatter injected by installer).
-- BMAD extension source files placed in correct location; BMAD deployment occurs during full `ma-agents` BMAD agent install via `lib/bmad.js` `STAGE:EXTENSION` logic.
-- `module-help.csv` entry inserted between Project Context Expansion and Sprint Status View rows (order does not affect functionality).
-- Both SKILL.md files implement identical workflow logic; BMAD version adds path resolution via `_bmad/bmm/config.yaml`.
-- Code review: All 8 acceptance criteria satisfied. No `backlog.yaml` write instructions found. Single-location invariant enforced via `sprint_item_ids` exclusion set. Orphan detection implemented with keep-not-remove policy. Validation step before atomic write.
-
-### Completion Checklist
-
-- [x] All task checkboxes marked complete
-- [x] Story status set to `review`
-- [x] sprint-status.yaml updated to `review` for 17-10
-- [x] File List populated below
-- [x] Change Log populated below
-
-## File List
-
-### Created
-- `skills/generate-backlog/skill.json` — IDE skill metadata
-- `skills/generate-backlog/SKILL.md` — IDE skill workflow (9 steps, installed to all agent directories)
-- `lib/bmad-extension/skills/generate-backlog/SKILL.md` — BMAD extension version with path resolution via config.yaml
-- `lib/bmad-extension/skills/generate-backlog/bmad-skill-manifest.yaml` — BMAD module manifest
-
-### Modified
-- `lib/bmad-extension/module-help.csv` — Added generate-backlog row for bmm-sm agent
-- `_bmad-output/implementation-artifacts/sprint-status.yaml` — Updated 17-10 status: ready-for-dev → review
-- `_bmad-output/implementation-artifacts/17-10-rework-generate-backlog.md` — This story file (tasks, status, dev record)
-
-### Deployed (by installer — not source files)
-- `.claude/skills/generate-backlog/SKILL.md` — Installed copy (frontmatter injected)
-- `.claude/skills/MANIFEST.yaml` — Updated with generate-backlog entry
-
-## Change Log
-
-| Date | Author | Change |
-|------|--------|--------|
-| 2026-04-06 | Dev Agent | Created IDE skill source files (skill.json + SKILL.md) |
-| 2026-04-06 | Dev Agent | Created BMAD extension files (SKILL.md + bmad-skill-manifest.yaml) |
-| 2026-04-06 | Dev Agent | Registered skill in module-help.csv for bmm-sm agent |
-| 2026-04-06 | Dev Agent | Ran installer — skill deployed to .claude/skills/generate-backlog/ |
-| 2026-04-06 | Dev Agent | Updated sprint-status.yaml: 17-10 → review |
-| 2026-04-06 | Dev Agent | Marked all task checkboxes complete; set story status to review |