PyAutoLabs · Jammy2211 · Jul 23, 2026 · Jul 23, 2026 · Jul 23, 2026
diff --git a/AGENTS.md b/AGENTS.md
@@ -157,7 +157,7 @@ the `/<verb>` slash commands.
 <!-- pyauto:commands:end -->
 
 Like the other PyAuto repos, PyAutoBrain runs from its checkout (no pip install);
-it resolves the sibling `pyauto-heart` and `autobuild` binaries from PATH or the
+it resolves the sibling `pyauto-heart` and `autohands` binaries from PATH or the
 `~/Code/PyAutoLabs/` checkouts.
 
 ## The command surface (Brain implicit)

diff --git a/ORGANISM.md b/ORGANISM.md
@@ -23,7 +23,7 @@ organs plan, build, test and release it, and you make every judgment call.
 *Hands* and *Build* name the **same organ** (PyAutoHands) throughout this
 document: the organ is the **Hands**, and *Build* is the call-chain step it
 performs. (The Hands repo was renamed PyAutoBuild → PyAutoHands; the *Build*
-call-chain shorthand and the `autobuild` package/CLI keep their names.
+call-chain shorthand and the `autohands` package/CLI keep their names.
 `PyAutoConf` likewise remains the Nerves repo's name, aligned with its
 `autoconf` package.)
 

diff --git a/agents/_common.sh b/agents/_common.sh
@@ -1,8 +1,8 @@
 #!/usr/bin/env bash
 # agents/_common.sh — shared helpers for PyAutoBrain's specialist agents.
 #
-# Resolves the sibling PyAuto organ CLIs (pyauto-heart, autobuild) the same way
-# the autobuild shim resolves them: prefer PATH, fall back to the sibling
+# Resolves the sibling PyAuto organ CLIs (pyauto-heart, autohands) the same way
+# the autohands shim resolves them: prefer PATH, fall back to the sibling
 # checkout under ~/Code/PyAutoLabs/. Nothing here is pip-installed.
 
 PYAUTO_ROOT="${PYAUTO_ROOT:-$HOME/Code/PyAutoLabs}"
@@ -31,8 +31,8 @@ resolve_heart() {
   _resolve_bin pyauto-heart "$PYAUTO_ROOT/PyAutoHeart/bin/pyauto-heart"
 }
 
-resolve_autobuild() {
-  _resolve_bin autobuild "$PYAUTO_ROOT/PyAutoHands/bin/autobuild"
+resolve_autohands() {
+  _resolve_bin autohands "$PYAUTO_ROOT/PyAutoHands/bin/autohands"
 }
 
 # _resolve_dir <env-var-name> <repo-name> — echo the path to a sibling PyAuto

diff --git a/agents/conductors/bug/_bug.py b/agents/conductors/bug/_bug.py
@@ -35,7 +35,8 @@
 # (the organs themselves), not library-source or workspace work.
 INFRA_TARGETS = {
     "pyautobrain": "PyAutoBrain", "pyautoheart": "PyAutoHeart",
-    "pyautobuild": "PyAutoHands", "autobuild": "PyAutoHands",
+    "pyautobuild": "PyAutoHands", "autohands": "PyAutoHands",
+    "autobuild": "PyAutoHands",  # back-compat: the package was renamed autobuild -> autohands
     "pyautomind": "PyAutoMind", "pyautomemory": "PyAutoMemory",
 }
 

diff --git a/agents/conductors/build/AGENTS.md b/agents/conductors/build/AGENTS.md
@@ -86,7 +86,7 @@ mode/action.
   "requested_action": "<PyAutoHands capability>",
   "health_status": "green|yellow|red|unknown",
   "decision": "proceed|proceed-with-caution|abort",
-  "execution_plan": ["autobuild <action> <args>"],
+  "execution_plan": ["autohands <action> <args>"],
   "execution_summary": "<one line>",
   "warnings": ["..."],
   "blockers": ["..."],

diff --git a/agents/conductors/build/BUILD_CAPABILITIES.md b/agents/conductors/build/BUILD_CAPABILITIES.md
@@ -2,12 +2,12 @@
 
 This audit records the execution surface the PyAutoBrain Build Agent reasons over
 and **calls**. The agent must treat every item here as a PyAutoHands capability,
-not as logic to reimplement inside Brain. Source of truth: the `autobuild`
-dispatcher (`PyAutoHands/bin/autobuild`) and `PyAutoHands/CLAUDE.md`.
+not as logic to reimplement inside Brain. Source of truth: the `autohands`
+dispatcher (`PyAutoHands/bin/autohands`) and `PyAutoHands/CLAUDE.md`.
 
 ## Execution capabilities (the Build Agent calls these)
 
-From `autobuild help`. **Mode** is the Build Agent allowlist that *may* route
+From `autohands help`. **Mode** is the Build Agent allowlist that *may* route
 the capability (`build.sh`); **Consumer today** is who actually drives it now.
 The two diverge for the workspace-run surface — see the note below.
 
@@ -24,26 +24,26 @@ The two diverge for the workspace-run surface — see the note below.
 | `script_matrix` | Output a JSON `{name, directory}` matrix for GitHub Actions. | build | **Heart** `workspace-validation.yml` (CI) |
 | `aggregate_results` | Aggregate per-job JSON into a release-readiness report. | build, release | **Heart** `workspace-validation.yml` (CI) |
 | `slow_skip_check` | Surface SLOW / NEEDS_FIX entries in workspace `no_run.yaml`. | build | `run_all.py` + Heart `test_run` check |
-| `repro_command` | Emit the shell command autobuild uses to run one script. | build | triage (manual handoff) |
+| `repro_command` | Emit the shell command autohands uses to run one script. | build | triage (manual handoff) |
 | `bump_colab_urls` | Rewrite Colab URLs in cwd from an old to a new date-tag. | build, deploy | `release.yml` (CI) + deploy |
 
 **Reading the Consumer column — the run\* seam is latent, not active.** The
-capabilities still *exist* and match the `autobuild` dispatcher and the
+capabilities still *exist* and match the `autohands` dispatcher and the
 `build.sh` allowlists exactly; the *Mode* column remains accurate as the
 allowlist of record. What changed is the driver. The workspace full-run →
 report → issue flow moved **out of `release.yml` into PyAutoHeart's
 `workspace-validation.yml`** (see `PyAutoHands/docs/internals.md` and the
 `release.yml` comment recording the removed `run_scripts` / `run_notebooks` /
 `analyze_results` jobs). Heart checks these primitives out from Build and reuses
 them directly — calling `run.py` / `run_python.py` / `script_matrix.py` /
-`aggregate_results.py`, **not** `autobuild run_*` and **not** `pyauto-brain build
+`aggregate_results.py`, **not** `autohands run_*` and **not** `pyauto-brain build
 run_*`. Nothing invokes `run` / `run_python` / `run_all` through the Build Agent
 today, so their build-mode allowlist entries are a **latent seam** — kept so the
 Build Agent could re-own execution without churn, but **Heart is the live
 consumer**. This is the execution/health boundary the audit below argues for,
 now made visible in the table itself.
 
-Underlying implementation assets the agent never re-owns: `autobuild/run_python.py`,
+Underlying implementation assets the agent never re-owns: `autohands/run_python.py`,
 `run.py`, `generate.py`, `script_matrix.py`, `aggregate_results.py`,
 `tag_and_merge.sh`, `build_util.py`, the `release.yml` GitHub workflow, and the
 per-workspace `config/build/{no_run,env_vars,visualise_notebooks}.yaml`.

diff --git a/agents/conductors/build/build.sh b/agents/conductors/build/build.sh
@@ -27,7 +27,7 @@
 #
 # Usage:
 #   build.sh [--mode build|deploy|release] [--force] [--accept-red=<reason>]...
-#            [--dry-run] [--json] [<action>] [-- <args forwarded to autobuild>]
+#            [--dry-run] [--json] [<action>] [-- <args forwarded to autohands>]
 #
 #   --force            proceed on a YELLOW verdict (deploy/release).
 #   --accept-red=<r>   authorize proceeding despite the RED reason <r>. Repeatable.
@@ -193,7 +193,7 @@ case "$eff" in
 esac
 
 # ----- execution plan -----
-plan_cmd="autobuild $action"
+plan_cmd="autohands $action"
 [[ ${#forward[@]} -gt 0 ]] && plan_cmd+=" ${forward[*]}"
 plan=("$plan_cmd")
 
@@ -250,6 +250,6 @@ if [[ "$dry_run" -eq 1 ]]; then
   exit 0
 fi
 
-autobuild="$(resolve_autobuild)" || exit $?
+autohands="$(resolve_autohands)" || exit $?
 [[ "$json_only" -eq 1 ]] || echo "== exec: $plan_cmd =="
-exec "$autobuild" "$action" "${forward[@]}"
+exec "$autohands" "$action" "${forward[@]}"
diff --git a/agents/conductors/clone/DESIGN.md b/agents/conductors/clone/DESIGN.md
@@ -121,7 +121,7 @@ bad usage).
    partition, generation plan, CloneDecision. No writer at all. Proves the
    reasoning on `PyAutoFit → autofit_assistant` as the dry-run case study.
 2. **v1 — seed births. SHIPPED.** `--apply` for **lightweight-seed** via a
-   PyAutoHands primitive (`autobuild/clone_seed.py`: repo creation + generic-set
+   PyAutoHands primitive (`autohands/clone_seed.py`: repo creation + generic-set
    copy + scaffolds + the `PENDING.md` growth queue). Heart gained the
    newborn-validation checklist (`PyAutoHeart/docs/newborn_validation.md`).
 3. **v2 — differentiated siblings.** Skill/wiki regeneration from the domain

diff --git a/agents/conductors/clone/_clone.py b/agents/conductors/clone/_clone.py
@@ -428,7 +428,7 @@ def apply_seed(args, decision):
     plan_path = Path(tempfile.mkstemp(prefix="clone_plan_", suffix=".json")[1])
     plan_path.write_text(json.dumps(plan, indent=2))
 
-    seed_script = PYAUTO_ROOT / "PyAutoHands" / "autobuild" / "clone_seed.py"
+    seed_script = PYAUTO_ROOT / "PyAutoHands" / "autohands" / "clone_seed.py"
     if not seed_script.exists():
         fail(4, f"Build primitive not found: {seed_script}")
     cmd = [sys.executable, str(seed_script), str(plan_path)]

diff --git a/agents/conductors/intake/_intake.py b/agents/conductors/intake/_intake.py
@@ -86,7 +86,8 @@
     "autogalaxy": "PyAutoGalaxy", "autolens": "PyAutoLens",
     "pyautomind": "PyAutoMind", "pyautobrain": "PyAutoBrain",
     "pyautoheart": "PyAutoHeart", "pyautobuild": "PyAutoHands",
-    "pyautomemory": "PyAutoMemory", "autobuild": "PyAutoHands",
+    "pyautomemory": "PyAutoMemory", "autohands": "PyAutoHands",
+    "autobuild": "PyAutoHands",  # back-compat: the package was renamed autobuild -> autohands
     "workspaces": "workspaces",
 }
 PRIORITY_HIGH = ["urgent", "asap", "blocker", "blocking", "critical", "important",

diff --git a/agents/conductors/release/AGENTS.md b/agents/conductors/release/AGENTS.md
@@ -19,7 +19,7 @@ Brain  →  Heart (gate)  →  Build (execute)
 2. **The release door**: plain `release [--force]` delegates the readiness gate
    *and* execution to the Build Agent's release mode
    (`build.sh --mode release`), the **single** gate implementation — GREEN
-   proceeds, YELLOW needs `--force`, RED blocks; on a pass `autobuild
+   proceeds, YELLOW needs `--force`, RED blocks; on a pass `autohands
    pre_build` dispatches `release.yml`. This conductor holds no second copy of
    that gate.
 

diff --git a/agents/conductors/release/release.sh b/agents/conductors/release/release.sh
@@ -70,7 +70,7 @@ echo "== release conductor: delegating gate + execution to the Build Agent (rele
 
 # One gate implementation, not two: the Build Agent's release mode refreshes
 # health via the vitals faculty, applies GREEN / YELLOW(--force) / RED, and on
-# a pass runs `autobuild pre_build` (which dispatches release.yml).
+# a pass runs `autohands pre_build` (which dispatches release.yml).
 args=(--mode release)
 [[ "$force" -eq 1 ]] && args+=(--force)
 for _a in ${accept_red[@]+"${accept_red[@]}"}; do args+=("--accept-red=$_a"); done

diff --git a/agents/faculties/vitals/HEART_CAPABILITIES.md b/agents/faculties/vitals/HEART_CAPABILITIES.md
@@ -92,7 +92,7 @@ reimplement inside Brain.
 
 PyAutoHands has been fully renamed onto the Heart/Brain names (no PyAutoPulse or
 PyAutoAgent references remain) and exposes health-shim commands such as
-`autobuild verify_install`, `autobuild url_check`, and `autobuild watch|status|tick|fix`.
+`autohands verify_install`, `autohands url_check`, and `autohands watch|status|tick|fix`.
 These delegate to the health authority rather than owning readiness logic.
 
 Decision: GREEN — the docs are renamed and the shims delegate only. Do not

diff --git a/bin/pyauto-brain b/bin/pyauto-brain
@@ -3,7 +3,7 @@
 #
 # PyAutoBrain is the reasoning layer of the PyAuto organism: it figures out HOW
 # work should be done and coordinates the organs that do it. The subcommand
-# pattern mirrors PyAutoHands/bin/autobuild and PyAutoHeart/bin/pyauto-heart so
+# pattern mirrors PyAutoHands/bin/autohands and PyAutoHeart/bin/pyauto-heart so
 # the CLIs feel the same. Agents live in two tiers under agents/:
 #
 #   agents/conductors/<name>/  — front-door agents a human DRIVES (they decide

diff --git a/config/policy.yaml b/config/policy.yaml
@@ -24,7 +24,7 @@ sizing_categories:
   workspace: [workspace, workspace_test, workspace_developer, howto, assistant, pipeline, project]
   organism: [organ]
 extra_workspace_targets: [workspaces]
-extra_organism_targets: [autobuild]
+extra_organism_targets: [autohands]
 
 # Keyword -> PyAutoMemory sub-wiki (also the science vocabulary difficulty
 # scoring keys off). Source of truth for the wiki list: PyAutoMemory/index.md.
@@ -58,7 +58,7 @@ target_signals:
   pyautomind: [pyautomind, the mind, prompt registry, active.md, planned.md,
                ideas.md, dashboard]
   pyautoheart: [heart, readiness, health check, vitals, green verdict]
-  pyautobuild: [autobuild, release.yml, notebook generation, the hands]
+  pyautobuild: [autohands, autobuild, release.yml, notebook generation, the hands]
 
 # Feature conductor: target -> the sub-wiki consulted by default.
 target_default_wiki:

diff --git a/docs/adoption/config_surfaces.md b/docs/adoption/config_surfaces.md
@@ -15,7 +15,7 @@ framework organs is domain-free logic you pull from upstream.
 | `agents/conductors/release/` — the library tuple + `nightly.sh` | Brain | Which libraries the release path drives. |
 | `agents/faculties/memory/` — the wiki keyword map | Brain | Topic keywords → your Memory's sub-wikis. |
 | `heart/readiness.py` — `DEFAULT_LIBRARIES`; `heart/checks/version_skew.py` — the workspace→(library, package) map | Heart | The release-gate repo sets. |
-| `autobuild/run_all.py`, `autobuild/slow_skip_check.py`, navigator maps | Hands | Which workspaces the validation pipeline runs and skips. |
+| `autohands/run_all.py`, `autohands/slow_skip_check.py`, navigator maps | Hands | Which workspaces the validation pipeline runs and skips. |
 
 The honest state: some of these are clean policy files (Heart's
 `config/repos.yaml`), others are constant tables inside code files. A

diff --git a/docs/organs/build.md b/docs/organs/build.md
@@ -18,7 +18,7 @@ work.
 
 ## The pieces
 
-- **`bin/autobuild`** — the single dispatcher; every operation is a
+- **`bin/autohands`** — the single dispatcher; every operation is a
   subcommand with `--help` (`pre_build`, `generate`, `run_all`,
   `tag_and_merge`, …).
 - **`pre_build.sh`** — the declarative heart of the pipeline: one
@@ -30,6 +30,6 @@ work.
 ## For an adopter
 
 Fork it. The pipeline mechanics are the framework; the `run_workspace`
-table in `pre_build.sh` and the small maps in `autobuild/*.py` (which
+table in `pre_build.sh` and the small maps in `autohands/*.py` (which
 workspaces to run, what to skip) are the declared config surfaces you
 rewrite for your own repos — see {doc}`../adoption/config_surfaces`.
diff --git a/skills/ship_library/reference.md b/skills/ship_library/reference.md
@@ -112,7 +112,7 @@ grep -rn "<old_function_or_class>" \
   euclid_strong_lens_modeling_pipeline/scripts/ HowToLens/scripts/
 ```
 
-Also check `PyAutoHands/autobuild/config/no_run.yaml` — a changed symbol used by
+Also check `PyAutoHands/autohands/config/no_run.yaml` — a changed symbol used by
 a script listed there is a **hidden risk** (its release-pipeline integration
 test is disabled). Present a data-driven recommendation:
 

diff --git a/tests/test_policy_seams.py b/tests/test_policy_seams.py
@@ -35,7 +35,7 @@ def test_workspace_and_organism_sets():
     assert "howtolens" in _sizing.WORKSPACE_REPOS
     assert "workspaces" in _sizing.WORKSPACE_REPOS  # policy extra
     assert "pyautobrain" in _sizing.ORGANISM_REPOS
-    assert "autobuild" in _sizing.ORGANISM_REPOS    # policy extra
+    assert "autohands" in _sizing.ORGANISM_REPOS    # policy extra
     # the three sets stay disjoint — a repo must classify one way
     assert not (_sizing.LIBRARY_REPOS & _sizing.WORKSPACE_REPOS)
     assert not (_sizing.LIBRARY_REPOS & _sizing.ORGANISM_REPOS)