ALDC-AL-Development-Collection / claude-plugin

# ALDC Plugin Instructions

<!-- Generated by scripts/sync-plugin-support.js. Do not edit. -->

This plugin runs the canonical ALDC contracts in the **Claude Code harness**. The
contracts were authored for GitHub Copilot Chat; every adapted file carries the
binding Copilot -> Claude Code mapping table at the top, plus the sha256 of the
canonical source it was generated from.

Read `${CLAUDE_PLUGIN_ROOT}/docs/claude-al-tooling.md` for this surface’s LSP/MCP bindings, then `${CLAUDE_PLUGIN_ROOT}/skills/skill-migrate/references/cli-al-tools.md` for the shared role/evidence contract. The Claude guide supersedes older capability-availability examples, never role responsibilities or human gates. Each agent and workflow links it explicitly, because a
plugin-root CLAUDE.md is not auto-loaded into a subagent.

## Roles

| Entry skill | Agent | Contract |
|---|---|---|
| `/aldc:architect` | `aldc:al-architect` | `${CLAUDE_PLUGIN_ROOT}/agents/al-architect.md` |
| `/aldc:spec` | `aldc:al-spec-agent` | `${CLAUDE_PLUGIN_ROOT}/agents/al-spec-agent.md` |
| `/aldc:conduct` | `aldc:al-conductor` | `${CLAUDE_PLUGIN_ROOT}/agents/al-conductor.md` |
| `/aldc:develop` | `aldc:al-developer` | `${CLAUDE_PLUGIN_ROOT}/agents/al-developer.md` |
| `/aldc:review` | `aldc:al-developer-reviewer` | `${CLAUDE_PLUGIN_ROOT}/agents/al-developer-reviewer.md` |
| `/aldc:triage` | `aldc:al-triage` | `${CLAUDE_PLUGIN_ROOT}/agents/al-triage.md` |
| `/aldc:presales` | `aldc:al-presales` | `${CLAUDE_PLUGIN_ROOT}/agents/al-presales.md` |
| `/aldc:agent-builder` | `aldc:al-agent-builder` | `${CLAUDE_PLUGIN_ROOT}/agents/al-agent-builder.md` |
| `/aldc:audit` | `aldc:dredd` | `${CLAUDE_PLUGIN_ROOT}/agents/dredd.md` |

The three TDD subagents (`aldc:al-planning-subagent`, `aldc:al-implement-subagent`,
`aldc:al-review-subagent`) are `user-invocable: false` in the canonical and have no
entry skill: only `aldc:al-conductor` launches them, through the `Task` tool.

## Workflows

Explicitly invoked; `disable-model-invocation: true` keeps the model from firing them.

| Skill | Canonical prompt |
|---|---|
| `/aldc:al-spec-create` | `prompts/al-spec.create.prompt.md` |
| `/aldc:al-build` | `prompts/al-build.prompt.md` |
| `/aldc:al-pr-prepare` | `prompts/al-pr-prepare.prompt.md` |
| `/aldc:al-memory-create` | `prompts/al-memory.create.prompt.md` |
| `/aldc:al-context-create` | `prompts/al-context.create.prompt.md` |
| `/aldc:al-initialize` | `prompts/al-initialize.prompt.md` |
| `/aldc:al-agent-create` | `prompts/al-agent.create.prompt.md` |
| `/aldc:al-agent-task` | `prompts/al-agent.task.prompt.md` |
| `/aldc:al-agent-instructions` | `prompts/al-agent.instructions.prompt.md` |
| `/aldc:al-agent-build-instructions` | `prompts/al-agent.build-instructions.prompt.md` |
| `/aldc:al-agent-test` | `prompts/al-agent.test.prompt.md` |

## Rules

Path-scoped AL rules live in `rules/`, each declaring exactly the globs its
canonical `applyTo` declares. `/aldc:al-initialize` copies them to the
project's `.claude/rules/` for auto-application.

## Plans

Requirement artifacts live under `.claude/plans/` on this surface
(`aldc.yaml -> plans.root`). The canonical repository keeps `.github/plans`, which
is what the Copilot deployment and the VS Code extension read.

## Mapping

| Copilot surface in the contract | Claude Code equivalent |
| --- | --- |
| `#runSubagent` / `runSubagent` / `agents:` | The `Task` tool with `subagent_type: "aldc:<agent>"`; one invocation carries everything inline (subagents are stateless) |
| `#askQuestions` / `vscode/askQuestions` | `AskUserQuestion` (main session only; a subagent returns its questions in its structured output) |
| `handoffs:` entries, and `send: false` on one | **No equivalent — the gate is yours to keep.** In Copilot a handoff is a button the human clicks, and `send: false` additionally hands them the prompt to review before it is sent; the host supplies the approval. Claude Code delegates through the `Task` tool, with no click and no review step. So never auto-delegate: present your output, get explicit approval, and only then delegate or route to another role. The handoff's routing is carried by the plugin's role entry skills; its human gate is carried by this rule |
| `@al-architect`, `@al-spec-agent`, `@al-conductor`, `@al-developer`, `@al-developer-reviewer`, `@al-triage`, `@al-presales`, `@al-agent-builder`, `@dredd` | `/aldc:architect`, `/aldc:spec`, `/aldc:conduct`, `/aldc:develop`, `/aldc:review`, `/aldc:triage`, `/aldc:presales`, `/aldc:agent-builder`, `/aldc:audit` (or `claude --agent aldc:<agent>`) |
| `@workspace use <workflow>` | `/aldc:<workflow>` with dots replaced by dashes (`al-spec.create` -> `/aldc:al-spec-create`); already rewritten below |
| `${input:Name}` prompt variables | Take the value from `$ARGUMENTS`; ask through `AskUserQuestion` when missing. Already rewritten below as `<Name from $ARGUMENTS>` |
| `execute` / `runInTerminal`, AL compilation or symbol restore | Developer/Implementer: discovered official AL MCP `mcp__al__al_compile` / `mcp__al__al_build` / `mcp__al__al_downloadsymbols`, or an installed ALTool/AL-Go runner through `Bash`. Use the correct App/Test project; unavailable capabilities are never simulated. Publishing retains its separate human/CI gate and is not granted by this adapter |
| `edit`, `read/readFile`, `search`, `#codebase` | `Edit`/`Write`, `Read`, `Grep`/`Glob` |
| `#changes`, `changes`, `search/changes` | Read-only `git status` / `git diff` through `Bash` only where granted; otherwise read the caller-supplied diff artifact or return the missing evidence request |
| `read/problems`, `al_get_diagnostics`, `#testFailure` | Discovered `mcp__al__al_getdiagnostics` for the explicit project, or actual compiler/test output. Diagnostics are not evidence of a fresh compile or executed tests. No result: record `not-run` / `unavailable` |
| `al-symbols-mcp/*`, `upstash/context7/*`, `microsoft-learn/*`, `microsoft-docs/*` | Tools named `mcp__al-symbols-mcp__*`, `mcp__context7__*`, `mcp__microsoft-docs__*` (or the `mcp__plugin_aldc_…` form). A server that is not loaded is `unavailable`; do not simulate it |
| `sshadowsdk.al-lsp-for-agents/*`, `#usages`, semantic definition/reference queries | Claude `LSP` with the existing AL LSP for Agents companion; discover the actual operations and project context first. VS Code tool identifiers are not Claude tool names |
| `ms-dynamics-smb.al/*`, `vscode.mermaid-chat-features/*` | VS Code tool identifiers do not exist here. Use only a separately discovered Claude capability; never rename community tools as Microsoft tools |
| `vscode/memory`, `vscode/*` | Not available; keep state in the canonical `.claude/plans/` artifacts of the project |
| `todo` | `TodoWrite` for in-session tracking; durable state stays in `.claude/plans/` |
| "load `skill-x`" | The `Skill` tool (`aldc:<skill-name>`) or read `${CLAUDE_PLUGIN_ROOT}/skills/<skill-name>/SKILL.md` |
| `.github/instructions/*.instructions.md` (`applyTo`) | `${CLAUDE_PLUGIN_ROOT}/rules/*.md` (`paths:`); `/aldc:al-initialize` copies them to the project's `.claude/rules/` for auto-apply in the main session; inject inline for subagents exactly as the contract says |
| `.github/skills/`, `.github/plans/…`, `docs/templates/` | `${CLAUDE_PLUGIN_ROOT}/skills/`, `.claude/plans/…` (project-owned, `aldc.yaml -> plans.root`), `${CLAUDE_PLUGIN_ROOT}/docs/templates/`; already rewritten below |
| `python …` runtime helpers, `--aldc-root` | Paths already point at `${CLAUDE_PLUGIN_ROOT}`; use `python` or `python3`, whichever exists (stdlib only) |
| `aldc.yaml` | `${CLAUDE_PROJECT_DIR}/aldc.yaml` when the project has one, otherwise `${CLAUDE_PLUGIN_ROOT}/aldc.yaml` |