feat: add Goose NeuralEngine adapter

agent-pack/CAPABILITY_MATRIX.md

@@ -12,21 +12,21 @@
 
 ## Matrix
 
-| Capability | OpenCode | Codex CLI |
-|---|---|---|
-| **Agents / roles** | SUPPORTED — `builder` (generic implementation), `arch-data-engineer` (specialist, scoped permissions), `reviewer` (read-only, restricted permissions), `planner` (read-only planning and routing), `mechanical` (deterministic low-judgment operations) | NOT YET ASSESSED — outside this NeuralEngine-only slice |
-| **Skills / contracts** | SUPPORTED — 5 skills: neuralengine, repository-review, python-project-validation, arch-linux-diagnostics, verification | SUPPORTED WITH LIMITATIONS — NeuralEngine contract projection only; other contracts remain unmapped |
-| **Global instructions** | SUPPORTED — `neuralengine-usage.md` loaded via `opencode.json` instructions array | SUPPORTED WITH LIMITATIONS — short `AGENTS.md` pointer; Codex CLI runtime discovery not exercised here |
-| **Permissions** | SUPPORTED — Agent-level permission blocks with allow/deny/ask for edit, bash, task, tools. Reviewer enforces read-only. | SUPPORTED WITH LIMITATIONS — Codex host sandbox/approval controls remain authoritative; no adapter write authority |
-| **Shell execution** | SUPPORTED — Scoped bash allowlist for `arch-data-engineer` (read-only diagnostics and validation; commit, push, destructive Git/filesystem/partitioning commands, and Ruff auto-fix denied). Restricted allowlist for `reviewer`. | SUPPORTED WITH LIMITATIONS — `neural` commands are ordinary host shell commands; executable/PATH/runtime behavior not verified |
-| **Repository instructions** | SUPPORTED — `AGENTS.md`, `CODEX.md`, `VISION.md`, `CONTEXT.md`, `pyproject.toml` awareness built into agent rules | SUPPORTED WITH LIMITATIONS — Codex CLI native `AGENTS.md` pointer for substantive/consequential work |
-| **NeuralEngine CLI** | SUPPORTED — `neural status` and `neural search` available and used in all reviews | SUPPORTED WITH LIMITATIONS — projection preserves `neural status`, targeted retrieval, and read-only boundaries; target installation not verified |
-| **Review** | SUPPORTED — `repository-review` skill, reviewer agent with read-only permissions, formal review format with verdict/checkpoint/validation/scope/findings | NOT YET ASSESSED |
-| **Verification** | SUPPORTED — reviewer agent with `verification` skill and enforced read-only command permissions (8 additional allow patterns: find, test, wc, sha256sum, diff, cmp, grep, sed). Quick Verification runs without permission prompts. | NOT YET ASSESSED |
-| **Certification** | SUPPORTED — Certification Report template, 3 verdicts (CERTIFIED/CERTIFIED WITH NOTES/NOT CERTIFIED), collision-safe naming, `.agent-work/certifications/` convention | NOT YET ASSESSED |
-| **Model selection** | SUPPORTED — Model configured in OpenCode runtime. Agent Pack is model-agnostic (DeepSeek V4 Pro Max, GPT-5.6 Sol Medium, others) | NOT YET ASSESSED |
-| **Non-interactive execution** | SUPPORTED WITH LIMITATIONS — Bash commands execute non-interactively. Human confirmation required only for restricted operations per permission model. | NOT YET ASSESSED |
-| **Artifact generation** | SUPPORTED — Review artifacts, certification reports, documentation files generated as markdown. No code generation or template engines. | NOT YET ASSESSED |
+| Capability | OpenCode | Codex CLI | Goose CLI/Desktop |
+|---|---|---|---|
+| **Agents / roles** | SUPPORTED — `builder` (generic implementation), `arch-data-engineer` (specialist, scoped permissions), `reviewer` (read-only, restricted permissions), `planner` (read-only planning and routing), `mechanical` (deterministic low-judgment operations) | NOT YET ASSESSED — outside this NeuralEngine-only slice | NOT YET ASSESSED — custom agents are outside this bounded slice |
+| **Skills / contracts** | SUPPORTED — 5 skills: neuralengine, repository-review, python-project-validation, arch-linux-diagnostics, verification | SUPPORTED WITH LIMITATIONS — NeuralEngine contract projection only; other contracts remain unmapped | SUPPORTED WITH LIMITATIONS — NeuralEngine contract projection only; other contracts remain unmapped |
+| **Global instructions** | SUPPORTED — `neuralengine-usage.md` loaded via `opencode.json` instructions array | SUPPORTED WITH LIMITATIONS — short `AGENTS.md` pointer; Codex CLI runtime discovery not exercised here | SUPPORTED WITH LIMITATIONS — short `AGENTS.md` pointer; Desktop launcher discovery remains environment-dependent |
+| **Permissions** | SUPPORTED — Agent-level permission blocks with allow/deny/ask for edit, bash, task, tools. Reviewer enforces read-only. | SUPPORTED WITH LIMITATIONS — Codex host sandbox/approval controls remain authoritative; no adapter write authority | SUPPORTED WITH LIMITATIONS — Goose host permission/approval controls remain authoritative; no adapter write authority |
+| **Shell execution** | SUPPORTED — Scoped bash allowlist for `arch-data-engineer` (read-only diagnostics and validation; commit, push, destructive Git/filesystem/partitioning commands, and Ruff auto-fix denied). Restricted allowlist for `reviewer`. | SUPPORTED WITH LIMITATIONS — `neural` commands are ordinary host shell commands; executable/PATH/runtime behavior not verified | SUPPORTED WITH LIMITATIONS — Developer shell tools are documented; executable/PATH/runtime behavior is target-environment dependent |
+| **Repository instructions** | SUPPORTED — `AGENTS.md`, `CODEX.md`, `VISION.md`, `CONTEXT.md`, `pyproject.toml` awareness built into agent rules | SUPPORTED WITH LIMITATIONS — Codex CLI native `AGENTS.md` pointer for substantive/consequential work | SUPPORTED WITH LIMITATIONS — Goose project context files are documented; exact Desktop conflict precedence remains unverified |
+| **NeuralEngine CLI** | SUPPORTED — `neural status` and `neural search` available and used in all reviews | SUPPORTED WITH LIMITATIONS — projection preserves `neural status`, targeted retrieval, and read-only boundaries; target installation not verified | SUPPORTED WITH LIMITATIONS — projection preserves `neural status`, targeted retrieval, and read-only boundaries; target installation and Desktop command availability not verified |
+| **Review** | SUPPORTED — `repository-review` skill, reviewer agent with read-only permissions, formal review format with verdict/checkpoint/validation/scope/findings | NOT YET ASSESSED | NOT YET ASSESSED — outside this bounded slice |
+| **Verification** | SUPPORTED — reviewer agent with `verification` skill and enforced read-only command permissions (8 additional allow patterns: find, test, wc, sha256sum, diff, cmp, grep, sed). Quick Verification runs without permission prompts. | NOT YET ASSESSED | NOT YET ASSESSED — outside this bounded slice |
+| **Certification** | SUPPORTED — Certification Report template, 3 verdicts (CERTIFIED/CERTIFIED WITH NOTES/NOT CERTIFIED), collision-safe naming, `.agent-work/certifications/` convention | NOT YET ASSESSED | NOT YET ASSESSED — outside this bounded slice |
+| **Model selection** | SUPPORTED — Model configured in OpenCode runtime. Agent Pack is model-agnostic (DeepSeek V4 Pro Max, GPT-5.6 Sol Medium, others) | NOT YET ASSESSED | NOT YET ASSESSED — outside this bounded slice |
+| **Non-interactive execution** | SUPPORTED WITH LIMITATIONS — Bash commands execute non-interactively. Human confirmation required only for restricted operations per permission model. | NOT YET ASSESSED | NOT YET ASSESSED — outside this bounded slice |
+| **Artifact generation** | SUPPORTED — Review artifacts, certification reports, documentation files generated as markdown. No code generation or template engines. | NOT YET ASSESSED | NOT YET ASSESSED — outside this bounded slice |
 
 ## Codex CLI assessment notes
 

agent-pack/MANIFEST.md

@@ -2,14 +2,14 @@
 
 ## Shared-to-platform mapping
 
-| Authoritative source | OpenCode target | Codex CLI target |
-|---|---|---|
-| `shared/neuralengine.md` | global instruction (`neuralengine-usage.md`) and NeuralEngine skill | `platforms/codex/skills/neuralengine/SKILL.md` (controlled copy; install target is `.agents/skills/neuralengine/SKILL.md`) |
-| `shared/repository-review.md` | repository-review skill | not mapped in this slice |
-| `shared/python-validation.md` | python-project-validation skill | not mapped in this slice |
-| `shared/arch-linux.md` | arch-linux-diagnostics skill | not mapped in this slice |
-| `shared/verification.md` | verification skill (Quick, Standard, and Certification implemented) | not mapped in this slice |
-| `shared/task-execution-policy.md` | no platform copy (vocabulary contract, deferred consumption) | no platform copy (vocabulary contract, deferred consumption) |
+| Authoritative source | OpenCode target | Codex CLI target | Goose CLI/Desktop target |
+|---|---|---|---|
+| `shared/neuralengine.md` | global instruction (`neuralengine-usage.md`) and NeuralEngine skill | `platforms/codex/skills/neuralengine/SKILL.md` (controlled copy; install target is `.agents/skills/neuralengine/SKILL.md`) | `platforms/goose/skills/neuralengine/SKILL.md` (controlled copy; install target is `.agents/skills/neuralengine/SKILL.md`) |
+| `shared/repository-review.md` | repository-review skill | not mapped in this slice | not mapped in this slice |
+| `shared/python-validation.md` | python-project-validation skill | not mapped in this slice | not mapped in this slice |
+| `shared/arch-linux.md` | arch-linux-diagnostics skill | not mapped in this slice | not mapped in this slice |
+| `shared/verification.md` | verification skill (Quick, Standard, and Certification implemented) | not mapped in this slice | not mapped in this slice |
+| `shared/task-execution-policy.md` | no platform copy (vocabulary contract, deferred consumption) | no platform copy (vocabulary contract, deferred consumption) | no platform copy (vocabulary contract, deferred consumption) |
 
 ## Platform-specific files (no shared equivalent)
 
@@ -20,6 +20,7 @@
 - `agents/planner.md`
 - `agents/mechanical.md`
 - `codex/AGENTS.md`
+- `goose/AGENTS.md`
 
 These files are platform-specific configuration artifacts. They have no
 corresponding shared source in this pack.

agent-pack/README.md

@@ -13,6 +13,7 @@ repository—not a separate product.
 - One complete platform variant (OpenCode) derived from the user's current,
   working OpenCode configuration.
 - One bounded Codex CLI NeuralEngine skill projection.
+- One bounded Goose CLI/Desktop NeuralEngine skill projection.
 - Placeholder directories for future Claude Code and Antigravity platform
   variants.
 
@@ -49,6 +50,7 @@ contract and introduces the generic builder agent:
 | ACP independent review | PASS |
 | OpenCode | Supported |
 | Codex CLI NeuralEngine slice | Supported with limitations (CLI only) |
+| Goose CLI/Desktop NeuralEngine slice | Supported with limitations (bounded post-v1.0 extension) |
 | Claude Code | Placeholder (not implemented) |
 | Antigravity | Placeholder (not implemented) |
 
@@ -213,6 +215,7 @@ OpenCode platform implementation:
 
 - [platforms/opencode/](platforms/opencode/) — OpenCode adapter and skills.
 - [platforms/codex/](platforms/codex/) — Codex CLI NeuralEngine adapter slice.
+- [platforms/goose/](platforms/goose/) — Goose CLI/Desktop NeuralEngine adapter slice.
 - [platforms/opencode/agents/planner.md](platforms/opencode/agents/planner.md) — Read-only planning and routing agent.
 - [platforms/opencode/agents/builder.md](platforms/opencode/agents/builder.md) — Generic builder agent (new in v0.4.0).
 - [platforms/opencode/agents/arch-data-engineer.md](platforms/opencode/agents/arch-data-engineer.md) — Specialist implementation agent.

agent-pack/platforms/goose/AGENTS.md

@@ -0,0 +1,7 @@
+# Goose CLI/Desktop NeuralEngine pointer
+
+For substantive or consequential work, consider the repository
+neuralengine skill at .agents/skills/neuralengine/SKILL.md.
+
+The semantic authority is agent-pack/shared/neuralengine.md. This pointer
+does not duplicate or redefine that contract.

agent-pack/platforms/goose/README.md

@@ -0,0 +1,51 @@
+# Goose CLI/Desktop Platform
+
+**Status:** NeuralEngine thin adapter implemented for Goose CLI/Desktop with
+documented limitations.
+
+This is one bounded provider projection of
+agent-pack/shared/neuralengine.md. It is a post-v1.0 extension of the Agent
+Pack and does not change the v1.0 platform freeze. It does not modify
+NeuralEngine runtime behavior, Brain persistence, schemas, APIs, or user-global
+Goose configuration.
+
+## Adapter files
+
+- AGENTS.md — minimal project-instruction pointer; merge this pointer into a
+  target repository's project instructions without replacing unrelated rules.
+- skills/neuralengine/SKILL.md — Goose-compatible project skill projection with
+  only the required name and description front matter.
+
+The skill body is a controlled copy of the shared contract. Drift validation
+requires the body after front matter removal to remain byte-equal to
+agent-pack/shared/neuralengine.md.
+
+## Manual installation mapping
+
+Installation is explicit and manual, consistent with the Agent Pack
+architecture:
+
+skills/neuralengine/SKILL.md
+→ <target-repository>/.agents/skills/neuralengine/SKILL.md
+
+The AGENTS.md content is a pointer to merge into the target repository's
+project instructions. This package does not provide an installer, write to
+user-global Goose configuration, or create a second semantic copy for Desktop.
+
+## Discovery and limitations
+
+- Goose documents AGENTS.md and .goosehints as project context files.
+- Goose documents project Agent Skills under .agents/skills/<name>/SKILL.md;
+  the .agents/skills projection is therefore shared by the CLI and Desktop
+  slice.
+- Goose CLI and Desktop expose host-controlled shell/tool permissions. The
+  adapter grants no additional read, write, Brain-write, staging, commit, push,
+  merge, tag, release, or publication authority.
+- The neural executable, PATH, Brain access, and command behavior must be
+  verified in each target environment. Desktop launchers may use a different
+  environment from an interactive shell.
+- Local verification found Goose CLI 1.45.0; Desktop version/help probing was
+  not independently available because the Electron launcher attempted read-only
+  host state and graphics/session initialization.
+
+No automatic installation or Brain write is performed.