axstack 0.12.1 → 0.13.1

package/README.md

@@ -26,7 +26,9 @@ without changing authority.
    substantial or stacked work needs an approved spec and matching ticket map.
 2. The current chat drives on whatever model runs it; there is no driver
    profile. Bind each ready task to the selected role snapshot and an authoritative Orca
-   Run, Task, and Dispatch. Exactly one writer owns a candidate at a time.
+   Run, Task, and Dispatch. Exactly one writer owns a candidate at a time. All
+   subagent and delegated worker dispatches go through Orca orchestration rather than
+   harness-native subagent tools.
 3. Peer PRs receive both configured independent reviewer roles. Authored PRs
    receive one eligible reviewer from the selected preset's explicit mapping
    and actual author provenance. Every review binds the exact head and base.
@@ -53,21 +55,23 @@ Orca with its runtime-owned guides. Filesystem access uses Bun's implementation
 of `node:fs` and `node:fs/promises`; there are no runtime dependencies.
 
 ```sh
-bun bin/axstack.js check --bundle . [--harness claude|codex]
+bun bin/axstack.js check --bundle . [--harness claude|codex|opencode|antigravity]
 bun bin/axstack.js install --bundle . --skills-dir <dir> --instructions <file> --preset mixed [--yes]
 bun bin/axstack.js install --bundle . --skills-dir <dir> --preset mixed
 bun bin/axstack.js uninstall --skills-dir <dir> --instructions <file>
 ```
 
-Use `--harness codex` or `--harness claude` only for a verified default skill
-directory. `--claude-settings` and `--no-claude-settings` manage the existing
+Use `--harness claude|codex|opencode|antigravity` only for a verified default
+skill directory and rules file. `--claude-settings` and `--no-claude-settings` manage the existing
 Claude Code subagent default transaction; they do not configure Orca roles.
 See [installation details](docs/installation.md).
 
-`--instructions` manages one versioned Axstack block in `AGENTS.md` or
-`CLAUDE.md`. Harness defaults resolve those files automatically. The block
-points at the installed entry skill and requires delegated work to use visible
-Orca orchestration rather than a harness-native subagent tool. Text and file
+`--instructions` manages one versioned Axstack block in `AGENTS.md`,
+`CLAUDE.md`, or `GEMINI.md`. Harness defaults resolve those files automatically. The block
+points at the installed entry skill and requires every subagent, delegated worker,
+reviewer, and cross-harness dispatch to use visible Orca orchestration via the `orca` CLI
+rather than a harness-native subagent tool (e.g. Claude/Codex native subagents). OpenCode
+and Antigravity subagents run as Orca-supervised workers. Text and file
 mode outside the markers are preserved; edited, malformed, unowned, or unsafe
 targets are reported without normal-path adoption. Install exits nonzero when
 an instruction conflict is preserved, while clean and idempotent installs exit
@@ -96,9 +100,9 @@ End-to-end compatibility remains unverified without matching runtime receipts.
 
 ## Runtime evidence and holds
 
-Native Orca exercises have returned Codex and Claude worker completions,
-same-terminal follow-up, separate worktree placement, settlement cleanup,
-`user_takeover` retention, and recovery from `consumer_fenced`. These are
+Native Orca exercises have returned Codex, Claude, and OpenCode Muse Spark
+worker completions, same-terminal follow-up, separate worktree placement, settlement
+cleanup, `user_takeover` retention, and recovery from `consumer_fenced`. These are
 bounded runtime facts, not proof that every role or harness is compatible.
 
 Input acceptance is not agent readiness. A trust prompt was observed after an

package/bin/axstack.js

@@ -60,8 +60,10 @@ Flags:
   --skills-dir <dir>  Explicit install target (required). Overrides --harness.
   --instructions <file>
                       Instruction file to receive the owned routing block.
-                      Harness defaults: ~/.claude/CLAUDE.md for Claude and
-                      $CODEX_HOME/AGENTS.md for Codex (default ~/.codex).
+                      Harness defaults: ~/.claude/CLAUDE.md for Claude,
+                      $CODEX_HOME/AGENTS.md for Codex (default ~/.codex),
+                      ~/.config/opencode/AGENTS.md for OpenCode, and
+                      ~/.gemini/GEMINI.md for Antigravity.
   --claude-settings <file>
                       Manage the Claude Code user settings file at this path.
                       This forces testable availability without installing Claude.
@@ -216,6 +218,8 @@ function resolveHarnessInstructions(harness) {
       : join(homeDir(), '.codex');
     return join(codexHome, 'AGENTS.md');
   }
+  if (harness === 'opencode') return join(homeDir(), '.config', 'opencode', 'AGENTS.md');
+  if (harness === 'antigravity') return join(homeDir(), '.gemini', 'GEMINI.md');
   return null;
 }
 

package/docs/installation.md

@@ -26,9 +26,14 @@ axstack install --preset <mixed|codex-only|claude-only> --bundle <dir> --skills-
 - `--skills-dir` is required unless a verified harness default resolves it.
 - `--instructions` selects the instruction file that receives Axstack's owned
   marker block. `--harness claude` defaults to `~/.claude/CLAUDE.md`;
-  `--harness codex` defaults to `$CODEX_HOME/AGENTS.md` or `~/.codex/AGENTS.md`.
-- `--harness` may resolve the documented `claude`, `codex`, or `opencode`
-  skill directory. Grok remains explicit-path only.
+  `--harness codex` defaults to `$CODEX_HOME/AGENTS.md` or `~/.codex/AGENTS.md`;
+  `--harness opencode` defaults to `~/.config/opencode/AGENTS.md`;
+  `--harness antigravity` defaults to `~/.gemini/GEMINI.md`.
+- `--harness` may resolve the documented `claude`, `codex`, `opencode`, or
+  `antigravity` skill directory. Grok remains explicit-path only. OpenCode also
+  reads `~/.claude/skills`, so its own directory is only needed for the owned
+  routing block; Antigravity (IDE and `agy` CLI) reads `~/.gemini/config/skills`
+  only.
 - `--claude-settings` and `--no-claude-settings` control the existing Claude
   Code subagent-default transaction. They do not configure Orca roles.
 - `--force` may replace an edited owned asset; it never adopts or removes
@@ -83,8 +88,11 @@ are pruned only when empty, and the target root is never removed.
 
 The deterministic `<!-- axstack:begin v1 -->` / `<!-- axstack:end -->` block
 contains the target-derived Axstack entry path and model-free routing prose. It
-also routes subagents, delegated workers, reviewers, and cross-harness work
-through Orca's `orca` CLI and forbids harness-native subagent delegation.
+also routes every subagent, delegated worker, reviewer, and cross-harness dispatch
+through Orca orchestration via the `orca` CLI (`orca-cli` / `orchestration` guides)
+so the work stays visible. It forbids harness-native subagent tools (e.g. Claude/Codex
+native subagents); workers such as OpenCode and Antigravity subagents
+run as Orca-supervised workers, never via harness-native delegation.
 
 Create, update, repeated install, check, and uninstall preserve every byte and
 the file mode outside the markers. The manifest binds the canonical instruction
@@ -184,6 +192,7 @@ survives.
 | Claude | `~/.claude/skills` | documented upstream |
 | Codex | `$CODEX_HOME/skills` (default `~/.codex/skills`) | documented upstream |
 | OpenCode | `~/.config/opencode/skills` | documented upstream |
+| Antigravity | `~/.gemini/config/skills` | documented upstream |
 | Grok | explicit `--skills-dir` only | auto-discovery unverified |
 
 Prefer explicit paths and current upstream CLI guidance. Installing files does

package/docs/workflows.md

@@ -78,6 +78,12 @@ one Orca executable, loads that binary's version-matched `orchestration` and
 `orca-cli` guides, and follows their advertised schemas. Axstack does not vendor
 the guides or restate a competing command protocol.
 
+All subagent, delegated-worker, reviewer, and cross-harness work goes through Orca
+orchestration via the `orca` CLI (`orca-cli` / `orchestration` guides). Do not use a
+harness-native subagent tool (e.g. Claude/Codex native subagents) for delegated work;
+use Orca runs, tasks, and dispatches instead so the work stays visible. OpenCode
+and Antigravity subagents run as Orca-supervised workers.
+
 Supervised work uses native Run, Task, and Dispatch identity. Preserve actual
 terminal, agent, worktree, requested/effective role, and revision receipts.
 `input_accepted` proves only terminal input; `turn_started` and session

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.12.1",
+  "version": "0.13.1",
   "description": "Axstack installer and setup CLI: installs owned chat skills and role data, configures supported harness settings, and checks Orca capabilities.",
   "keywords": [
     "claude-code",

package/src/locations.js

@@ -29,7 +29,15 @@ export function harnessLocations() {
       discovery: 'docs',
       source: 'https://opencode.ai/docs/skills',
       notes:
-        'Global skills directory from OpenCode docs; confirm with local help. Pass --skills-dir to override.',
+        'Global skills directory from OpenCode docs; OpenCode also reads ~/.claude/skills and ~/.agents/skills. Pass --skills-dir to override.',
+    },
+    {
+      harness: 'antigravity',
+      skillsDir: '~/.gemini/config/skills',
+      discovery: 'docs',
+      source: 'https://antigravity.google/docs/skills',
+      notes:
+        'Global skills directory shared by the Antigravity IDE and agy CLI per Google docs (confirmed with agy 2026-09-17; the older ~/.gemini/antigravity/skills path is not read). Pass --skills-dir to override.',
     },
     {
       harness: 'grok',