eai-cli 0.0.0-bootstrap.0

package/resources/gofer/commands/gofer_spec_summary.md

@@ -0,0 +1,87 @@
+---
+name: gofer:spec-summary
+description: "Generate a business-friendly summary of feature value and scope."
+title: 'Gofer Spec Summary'
+category: control
+surfaces:
+  - claude
+  - claude-mirror
+  - copilot
+  - vscode
+  - codex
+  - gemini
+  - github-prompts
+  - agents-skills
+  - system-skills
+---
+
+# Gofer Spec Summary
+
+## EAI Platform Session Preflight
+
+Before any Gofer stage/helper command does pipeline work:
+
+1. Treat durable delivery as EAI Platform delivery by default, with Azure second
+   and every other stack only by explicit exception.
+2. Run `eai whoami` and confirm the EAI CLI is installed, the user is logged in,
+   and an active tenant is visible.
+3. If `eai` is missing, `eai whoami` fails, the token is expired, or no active
+   tenant is available, stop and run `/gofer:eai-first-run` or ask the user to
+   approve login/setup before continuing.
+4. For EAI app delivery, do not continue into research, specification, planning,
+   tasks, implementation, or validation until
+   `.specify/specs/{feature}/eai-preflight.md` records login, tenant, template,
+   app-readiness, and next-action evidence.
+5. Do not write tokens, secrets, private tenant IDs, or local `.env` values into
+   Gofer artifacts; record only product-safe readiness status and evidence.
+
+## Token And Cost Policy
+<!-- gofer:token-cost-policy:start -->
+
+Before spawning agents, calling tools, or loading large files:
+
+1. Treat `.specify/memory/gofer-model-policy.yaml` as the repo-owned source of truth for simple, medium, hard, and arbiter model routing. If it is missing, run `/gofer:bootstrap-workspace` before continuing.
+2. Use the cheapest capable model first.
+   - Claude: Haiku for scouting/extraction; Sonnet for normal implementation, synthesis, validation, and security; Opus for high-risk arbitration or release-critical failures.
+   - Codex/OpenAI: GPT mini for simple coding; GPT nano only for locate/classify/summarize/mechanical work; GPT-5.3-Codex or flagship GPT for tool-heavy coding, architecture, and release-critical validation.
+   - Gemini: Flash-Lite for cheap large-context scan/summarize; Flash for default research synthesis; Pro for large-context architecture or high-risk arbitration.
+   - Copilot: prefer Auto for simple and default work; ask the user before choosing a paid/high-tier picker model for hard security, architecture, or release gates.
+3. Keep raw tool output out of the main conversation context. Save stable findings to `.specify/specs/{feature}/context-bundle.md`, then work from summaries.
+4. Use provider prompt/context caching only for stable, non-secret prefixes: Gofer scaffold, AGENTS/CLAUDE/Copilot instructions, constitution, repo map, stage contracts, and validation rubric.
+5. Before continuing after large research, planning, implementation, or validation bursts, checkpoint the durable artifacts and compact/clear/resume context when the host supports it.
+6. Escalate model tier only when a cheaper pass is low-confidence, contradictory, security-sensitive, or blocking release quality.
+<!-- gofer:token-cost-policy:end -->
+
+Generate a business-friendly summary of the current feature and write it to
+`.specify/specs/{feature}/spec-summary.md`.
+
+Use this when a stakeholder or implementation team needs the plain-language
+purpose, expected outcomes, and scope boundaries without diving into the full
+spec.
+
+When you run this helper:
+
+1. Read the approved feature-local artifacts (`spec.md`, `plan.md`,
+   `contract-pack.md`, `quickstart.md`) and summarize only what is already in
+   scope.
+2. Keep the summary business-facing and humble. Do not turn it into a PRD or an
+   issue-tracker export.
+3. Write the artifact only to `.specify/specs/{feature}/spec-summary.md`.
+4. If the target file already exists, replace it and prepend a regeneration note
+   such as `<!-- regenerated at [ISO timestamp] -->`.
+5. Include the minimum provenance schema:
+   - `GeneratedAt`
+   - `SourceCommandId`
+   - `SourceInputs`
+   - `OverwriteNoticeWhenApplicable`
+
+The generated summary must contain these sections:
+
+- `## Provenance`
+- `## What`
+- `## Why`
+- `## Acceptance Criteria`
+- `## Out of Scope`
+
+Keep the content Gofer-owned. Do not copy upstream Matt Pocock skill text
+verbatim.

package/resources/gofer/commands/gofer_tdd.md

@@ -0,0 +1,87 @@
+---
+name: gofer:tdd
+description: "Guide a red-green-refactor loop tied to spec acceptance criteria."
+title: 'Gofer TDD'
+category: control
+surfaces:
+  - claude
+  - claude-mirror
+  - copilot
+  - vscode
+  - codex
+  - gemini
+  - github-prompts
+  - agents-skills
+  - system-skills
+---
+
+# Gofer TDD
+
+## EAI Platform Session Preflight
+
+Before any Gofer stage/helper command does pipeline work:
+
+1. Treat durable delivery as EAI Platform delivery by default, with Azure second
+   and every other stack only by explicit exception.
+2. Run `eai whoami` and confirm the EAI CLI is installed, the user is logged in,
+   and an active tenant is visible.
+3. If `eai` is missing, `eai whoami` fails, the token is expired, or no active
+   tenant is available, stop and run `/gofer:eai-first-run` or ask the user to
+   approve login/setup before continuing.
+4. For EAI app delivery, do not continue into research, specification, planning,
+   tasks, implementation, or validation until
+   `.specify/specs/{feature}/eai-preflight.md` records login, tenant, template,
+   app-readiness, and next-action evidence.
+5. Do not write tokens, secrets, private tenant IDs, or local `.env` values into
+   Gofer artifacts; record only product-safe readiness status and evidence.
+
+## Token And Cost Policy
+<!-- gofer:token-cost-policy:start -->
+
+Before spawning agents, calling tools, or loading large files:
+
+1. Treat `.specify/memory/gofer-model-policy.yaml` as the repo-owned source of truth for simple, medium, hard, and arbiter model routing. If it is missing, run `/gofer:bootstrap-workspace` before continuing.
+2. Use the cheapest capable model first.
+   - Claude: Haiku for scouting/extraction; Sonnet for normal implementation, synthesis, validation, and security; Opus for high-risk arbitration or release-critical failures.
+   - Codex/OpenAI: GPT mini for simple coding; GPT nano only for locate/classify/summarize/mechanical work; GPT-5.3-Codex or flagship GPT for tool-heavy coding, architecture, and release-critical validation.
+   - Gemini: Flash-Lite for cheap large-context scan/summarize; Flash for default research synthesis; Pro for large-context architecture or high-risk arbitration.
+   - Copilot: prefer Auto for simple and default work; ask the user before choosing a paid/high-tier picker model for hard security, architecture, or release gates.
+3. Keep raw tool output out of the main conversation context. Save stable findings to `.specify/specs/{feature}/context-bundle.md`, then work from summaries.
+4. Use provider prompt/context caching only for stable, non-secret prefixes: Gofer scaffold, AGENTS/CLAUDE/Copilot instructions, constitution, repo map, stage contracts, and validation rubric.
+5. Before continuing after large research, planning, implementation, or validation bursts, checkpoint the durable artifacts and compact/clear/resume context when the host supports it.
+6. Escalate model tier only when a cheaper pass is low-confidence, contradictory, security-sensitive, or blocking release quality.
+<!-- gofer:token-cost-policy:end -->
+
+Guide a red-green-refactor loop for the active feature and write the cycle log
+to `.specify/specs/{feature}/tdd-session.md`.
+
+Use this helper when you want to work test-first inside the existing Gofer
+implementation flow without replacing `/5_gofer_implement` or `/9_gofer_tests`.
+
+When you run this helper:
+
+1. Read the feature acceptance criteria and the current task scope before
+   proposing test changes.
+2. Define the smallest failing test that proves the next slice of behavior is
+   missing.
+3. Keep the cycle explicit: red, green, then refactor.
+4. Record only feature-local artifacts and paths.
+5. Write the artifact only to `.specify/specs/{feature}/tdd-session.md`.
+6. If the target file already exists, replace it and prepend a regeneration note
+   such as `<!-- regenerated at [ISO timestamp] -->`.
+7. Include the minimum provenance schema:
+   - `GeneratedAt`
+   - `SourceCommandId`
+   - `SourceInputs`
+   - `OverwriteNoticeWhenApplicable`
+
+The generated TDD session must contain these sections:
+
+- `## Provenance`
+- `## Acceptance Criteria Linkage`
+- `## Red`
+- `## Green`
+- `## Refactor`
+
+Keep the content Gofer-owned. Do not copy upstream Matt Pocock skill text
+verbatim.

package/resources/gofer/commands/gofer_vocabulary.md

@@ -0,0 +1,87 @@
+---
+name: gofer:vocabulary
+description: "Extract domain terminology into a canonical feature glossary."
+title: 'Gofer Vocabulary'
+category: control
+surfaces:
+  - claude
+  - claude-mirror
+  - copilot
+  - vscode
+  - codex
+  - gemini
+  - github-prompts
+  - agents-skills
+  - system-skills
+---
+
+# Gofer Vocabulary
+
+## EAI Platform Session Preflight
+
+Before any Gofer stage/helper command does pipeline work:
+
+1. Treat durable delivery as EAI Platform delivery by default, with Azure second
+   and every other stack only by explicit exception.
+2. Run `eai whoami` and confirm the EAI CLI is installed, the user is logged in,
+   and an active tenant is visible.
+3. If `eai` is missing, `eai whoami` fails, the token is expired, or no active
+   tenant is available, stop and run `/gofer:eai-first-run` or ask the user to
+   approve login/setup before continuing.
+4. For EAI app delivery, do not continue into research, specification, planning,
+   tasks, implementation, or validation until
+   `.specify/specs/{feature}/eai-preflight.md` records login, tenant, template,
+   app-readiness, and next-action evidence.
+5. Do not write tokens, secrets, private tenant IDs, or local `.env` values into
+   Gofer artifacts; record only product-safe readiness status and evidence.
+
+## Token And Cost Policy
+<!-- gofer:token-cost-policy:start -->
+
+Before spawning agents, calling tools, or loading large files:
+
+1. Treat `.specify/memory/gofer-model-policy.yaml` as the repo-owned source of truth for simple, medium, hard, and arbiter model routing. If it is missing, run `/gofer:bootstrap-workspace` before continuing.
+2. Use the cheapest capable model first.
+   - Claude: Haiku for scouting/extraction; Sonnet for normal implementation, synthesis, validation, and security; Opus for high-risk arbitration or release-critical failures.
+   - Codex/OpenAI: GPT mini for simple coding; GPT nano only for locate/classify/summarize/mechanical work; GPT-5.3-Codex or flagship GPT for tool-heavy coding, architecture, and release-critical validation.
+   - Gemini: Flash-Lite for cheap large-context scan/summarize; Flash for default research synthesis; Pro for large-context architecture or high-risk arbitration.
+   - Copilot: prefer Auto for simple and default work; ask the user before choosing a paid/high-tier picker model for hard security, architecture, or release gates.
+3. Keep raw tool output out of the main conversation context. Save stable findings to `.specify/specs/{feature}/context-bundle.md`, then work from summaries.
+4. Use provider prompt/context caching only for stable, non-secret prefixes: Gofer scaffold, AGENTS/CLAUDE/Copilot instructions, constitution, repo map, stage contracts, and validation rubric.
+5. Before continuing after large research, planning, implementation, or validation bursts, checkpoint the durable artifacts and compact/clear/resume context when the host supports it.
+6. Escalate model tier only when a cheaper pass is low-confidence, contradictory, security-sensitive, or blocking release quality.
+<!-- gofer:token-cost-policy:end -->
+
+Extract the feature's shared domain language into a canonical glossary and
+write it to `.specify/specs/{feature}/glossary.md`.
+
+Use this when research, specification, contracts, or implementation rely on
+terms that need stable definitions across Claude, Copilot, Codex, and Gemini
+surfaces.
+
+When you run this helper:
+
+1. Read the feature-local context that already exists (`research.md`, `spec.md`,
+   `plan.md`, `contracts/`, `quickstart.md`) and ignore unrelated repository
+   content.
+2. Identify project-specific terms, acronyms, role names, workflow names, and
+   overloaded words that need precise definitions.
+3. Write the artifact only to `.specify/specs/{feature}/glossary.md`. Never
+   write to repo root or any provider-specific surface directory.
+4. If the target file already exists, replace it and prepend a regeneration note
+   such as `<!-- regenerated at [ISO timestamp] -->`.
+5. Include the minimum provenance schema:
+   - `GeneratedAt`
+   - `SourceCommandId`
+   - `SourceInputs`
+   - `OverwriteNoticeWhenApplicable`
+
+The generated glossary must contain these sections:
+
+- `## Provenance`
+- `## Term Entries`
+- `## Definitions`
+- `## Source Artifacts`
+
+Keep the content Gofer-owned and concise. Do not copy upstream Matt Pocock
+skill text verbatim.

package/resources/gofer/commands/gofer_zoom_out.md

@@ -0,0 +1,87 @@
+---
+name: gofer:zoom-out
+description: "Show how the current feature connects to broader system boundaries."
+title: 'Gofer Zoom Out'
+category: control
+surfaces:
+  - claude
+  - claude-mirror
+  - copilot
+  - vscode
+  - codex
+  - gemini
+  - github-prompts
+  - agents-skills
+  - system-skills
+---
+
+# Gofer Zoom Out
+
+## EAI Platform Session Preflight
+
+Before any Gofer stage/helper command does pipeline work:
+
+1. Treat durable delivery as EAI Platform delivery by default, with Azure second
+   and every other stack only by explicit exception.
+2. Run `eai whoami` and confirm the EAI CLI is installed, the user is logged in,
+   and an active tenant is visible.
+3. If `eai` is missing, `eai whoami` fails, the token is expired, or no active
+   tenant is available, stop and run `/gofer:eai-first-run` or ask the user to
+   approve login/setup before continuing.
+4. For EAI app delivery, do not continue into research, specification, planning,
+   tasks, implementation, or validation until
+   `.specify/specs/{feature}/eai-preflight.md` records login, tenant, template,
+   app-readiness, and next-action evidence.
+5. Do not write tokens, secrets, private tenant IDs, or local `.env` values into
+   Gofer artifacts; record only product-safe readiness status and evidence.
+
+## Token And Cost Policy
+<!-- gofer:token-cost-policy:start -->
+
+Before spawning agents, calling tools, or loading large files:
+
+1. Treat `.specify/memory/gofer-model-policy.yaml` as the repo-owned source of truth for simple, medium, hard, and arbiter model routing. If it is missing, run `/gofer:bootstrap-workspace` before continuing.
+2. Use the cheapest capable model first.
+   - Claude: Haiku for scouting/extraction; Sonnet for normal implementation, synthesis, validation, and security; Opus for high-risk arbitration or release-critical failures.
+   - Codex/OpenAI: GPT mini for simple coding; GPT nano only for locate/classify/summarize/mechanical work; GPT-5.3-Codex or flagship GPT for tool-heavy coding, architecture, and release-critical validation.
+   - Gemini: Flash-Lite for cheap large-context scan/summarize; Flash for default research synthesis; Pro for large-context architecture or high-risk arbitration.
+   - Copilot: prefer Auto for simple and default work; ask the user before choosing a paid/high-tier picker model for hard security, architecture, or release gates.
+3. Keep raw tool output out of the main conversation context. Save stable findings to `.specify/specs/{feature}/context-bundle.md`, then work from summaries.
+4. Use provider prompt/context caching only for stable, non-secret prefixes: Gofer scaffold, AGENTS/CLAUDE/Copilot instructions, constitution, repo map, stage contracts, and validation rubric.
+5. Before continuing after large research, planning, implementation, or validation bursts, checkpoint the durable artifacts and compact/clear/resume context when the host supports it.
+6. Escalate model tier only when a cheaper pass is low-confidence, contradictory, security-sensitive, or blocking release quality.
+<!-- gofer:token-cost-policy:end -->
+
+Expand the current feature into its surrounding system context and write the
+result to `.specify/specs/{feature}/zoom-out-report.md`.
+
+Use this helper when the feature needs broader architectural framing: upstream
+dependencies, downstream consumers, or cross-cutting risks that are easy to
+miss inside a narrow task view.
+
+When you run this helper:
+
+1. Read the approved feature-local artifacts and identify the current boundary
+   being changed.
+2. Map the upstream inputs, downstream consumers, and cross-cutting impacts that
+   materially affect the feature.
+3. Keep the output feature-local and architecture-focused.
+4. Write the artifact only to
+   `.specify/specs/{feature}/zoom-out-report.md`.
+5. If the target file already exists, replace it and prepend a regeneration note
+   such as `<!-- regenerated at [ISO timestamp] -->`.
+6. Include the minimum provenance schema:
+   - `GeneratedAt`
+   - `SourceCommandId`
+   - `SourceInputs`
+   - `OverwriteNoticeWhenApplicable`
+
+The generated zoom-out report must contain these sections:
+
+- `## Provenance`
+- `## Current Boundary`
+- `## Upstream/Downstream`
+- `## Cross-Cutting Impact`
+
+Keep the content Gofer-owned. Do not copy upstream Matt Pocock skill text
+verbatim.

package/resources/gofer/copilot-instructions/gofer-cost.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**"
+---
+
+# Gofer Token And Cost Policy
+
+Before running Gofer stages, spawning agents, or loading large files:
+
+- Treat `.specify/memory/gofer-model-policy.yaml` as the repo-owned model policy. Use Copilot `Auto` for simple/default work unless the user explicitly chooses a specific model.
+- Use the cheapest capable model first. Escalate only when a cheaper pass is low-confidence, contradictory, security-sensitive, release-critical, or blocking quality.
+- Keep raw search, build, and test output out of the main chat context. Write stable findings to `.specify/specs/{feature}/context-bundle.md` and continue from summaries.
+- Prefer provider prompt/context caching for stable non-secret prefixes: Gofer scaffold, repository instructions, constitution, repo map, stage contracts, and validation rubric.
+- After large research, planning, implementation, or validation bursts, checkpoint artifacts and compact/clear/resume context when the host supports it.

package/resources/gofer/copilot-instructions/language-server.instructions.md

@@ -0,0 +1,49 @@
+---
+applyTo: 'language-server/**/*'
+---
+
+# Language Server Development Instructions
+
+You are working on the Gofer Language Server.
+
+## Architecture
+
+The Language Server provides dual protocol support:
+
+1. **LSP (Language Server Protocol)** - Communication with VSCode extension
+2. **MCP (Model Context Protocol)** - Communication with AI assistants
+
+## Key Files
+
+- **Server Entry**: `language-server/src/server.ts`
+- **MCP Tools**: `language-server/src/mcp/toolHandler.ts`
+- **Spec Loader**: `language-server/src/utils/goferLoader.ts`
+
+## MCP Tools (6 Total)
+
+| Tool                       | Purpose                             |
+| -------------------------- | ----------------------------------- |
+| `gofer_get_specs`          | List all specs and tasks            |
+| `gofer_get_next_task`      | Get next task based on dependencies |
+| `gofer_execute_task`       | Mark task in-progress, get context  |
+| `gofer_update_task_status` | Mark task completed/failed          |
+| `gofer_validate_code`      | Check against constitution          |
+| `gofer_run_tests`          | Execute Playwright tests            |
+
+## Adding New MCP Tools
+
+1. Define tool in `server.ts` tool capabilities
+2. Implement handler in `mcp/toolHandler.ts`
+3. Register in MCP tool list
+4. Test via Claude Code or Copilot
+
+## LSP Capabilities
+
+- textDocument/completion - Spec suggestions
+- textDocument/hover - Spec details
+- Custom methods for spec operations
+
+## Dependencies
+
+- vscode-languageserver 9.0.1
+- Static validation service (no direct model SDK/API key dependency)

package/resources/gofer/copilot-instructions/typescript.instructions.md

@@ -0,0 +1,47 @@
+---
+applyTo: '**/*.ts,**/*.tsx'
+---
+
+# TypeScript Development Instructions
+
+You are working on Gofer, a TypeScript project using:
+
+- TypeScript 5.7.2 with strict mode
+- Node.js 18+ (ES2022 modules)
+- VSCode Extension API
+- vscode-languageserver 9.0.1
+
+## Code Quality Standards
+
+1. **Type Safety**
+   - Never use `any` type - use `unknown` and narrow with type guards
+   - Always provide explicit return types for functions
+   - Use interface over type for object shapes when possible
+   - Prefer union types over enums for string literals
+
+2. **Imports**
+   - Use ES6 imports (not `require()`)
+   - Use `.js` extension in imports for ESM compatibility
+   - Group imports: external → project → relative
+
+3. **Async/Await**
+   - Always use async/await over raw Promises
+   - Handle errors with try/catch, not `.catch()`
+   - Use `Promise.all()` for parallel operations
+
+4. **Documentation**
+   - Add JSDoc comments for public APIs
+   - Document parameters and return types
+   - Include @throws for functions that can throw
+
+## File Structure
+
+- Keep files under 300 lines
+- One class/component per file
+- Export from index files for modules
+
+## Testing
+
+- Write tests before implementation (TDD)
+- Minimum 80% code coverage
+- Use descriptive test names: `should [action] when [condition]`

package/resources/gofer/copilot-instructions/vscode-extension.instructions.md

@@ -0,0 +1,46 @@
+---
+applyTo: 'extension/**/*'
+---
+
+# VSCode Extension Development Instructions
+
+You are working on the Gofer VSCode extension.
+
+## Key Architecture
+
+- **Extension entry**: `extension/src/extension.ts`
+- **LSP Client**: `extension/src/lspClient.ts` - Connects to Language Server
+- **MCP Config**: `extension/src/mcpConfig.ts` - Creates `.vscode/mcp.json`
+- **Spec Parser**: `extension/src/goferParser.ts` - Parses GitHub Gofer format
+
+## VSCode APIs to Use
+
+- `vscode.workspace` for file operations
+- `vscode.window` for UI (notifications, input, quick picks)
+- `vscode.commands` for registering commands
+- `vscode.TreeDataProvider` for tree views
+
+## Important Patterns
+
+1. **Activation Events**
+   - Extension activates on workspace open with `.specify/` folder
+   - Use `workspaceContains` activation events
+
+2. **Command Registration**
+   - All commands prefixed with `gofer.`
+   - Register in `extension.ts` activate()
+   - Dispose properly in deactivate()
+
+3. **Resource Bundling**
+   - Bundled resources in `extension/resources/`
+   - Copy to workspace during initialization
+   - Use webpack for production bundling
+
+4. **Settings**
+   - Contribute through `package.json` contributes.configuration
+   - Access via `vscode.workspace.getConfiguration('gofer')`
+
+## Testing
+
+- Use @vscode/test-electron for integration tests
+- Mock vscode APIs for unit tests