claude-turing 4.7.0 → 4.8.1

package/commands/explore.md

@@ -1,9 +1,8 @@
 ---
 name: explore
 description: Tree-search-guided hypothesis exploration using AB-MCTS. Explores the space of experiment ideas as a search tree, scored by the critique engine. Discovers non-obvious refinement chains that linear suggestion cannot find.
-disable-model-invocation: true
 argument-hint: "[ml/project] [--iterations N] [--top N] [--strategy abmcts-a|abmcts-m|greedy]"
-allowed-tools: Read, Write, Bash(python scripts/*:*, source .venv/bin/activate:*), Grep, Glob
+allowed-tools: Read, Write, Bash(uv run python scripts/*:*, uv sync:*), Grep, Glob
 ---
 
 Explore the hypothesis space using tree search. Instead of suggesting independent ideas, this builds and searches a tree of refinement chains — each node is a hypothesis scored by novelty, feasibility, and expected impact.
@@ -32,7 +31,7 @@ Extract from `$ARGUMENTS`:
 ### 1. Assess Current State
 
 ```bash
-source .venv/bin/activate && python scripts/show_metrics.py --last 10 2>/dev/null || echo "No experiments yet"
+uv run python scripts/show_metrics.py --last 10 2>/dev/null || echo "No experiments yet"
 ```
 
 Read `config.yaml` to understand the current model and metric.
@@ -40,7 +39,7 @@ Read `config.yaml` to understand the current model and metric.
 ### 2. Run Tree Search
 
 ```bash
-source .venv/bin/activate && python scripts/treequest_suggest.py \
+uv run python scripts/treequest_suggest.py \
     --log experiments/log.jsonl \
     --config config.yaml \
     --top <N> \
@@ -59,7 +58,7 @@ The script will:
 For each result, add to the hypothesis queue:
 
 ```bash
-source .venv/bin/activate && python scripts/manage_hypotheses.py add "<description>" \
+uv run python scripts/manage_hypotheses.py add "<description>" \
     --priority medium --source treequest
 ```
 

package/commands/export.md

@@ -1,7 +1,6 @@
 ---
 name: export
 description: Export model to production format with equivalence verification, latency benchmarking, and deployment model card.
-disable-model-invocation: true
 argument-hint: "[exp-id] [--format joblib|xgboost_json|onnx|torchscript|tflite]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Export a trained model to a production-ready format.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -24,7 +23,7 @@ Export a trained model to a production-ready format.
 
 3. **Run export pipeline:**
    ```bash
-   python scripts/export_model.py $ARGUMENTS
+   uv run python scripts/export_model.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/commands/feature.md

@@ -1,7 +1,6 @@
 ---
 name: feature
 description: Automated feature selection — multi-method importance consensus, redundancy detection, and interaction feature generation.
-disable-model-invocation: true
 argument-hint: "[--method all|importance] [--top-k 20]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Systematically evaluate which features matter and which are noise.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -22,7 +21,7 @@ Systematically evaluate which features matter and which are noise.
 
 3. **Run feature analysis:**
    ```bash
-   python scripts/feature_intelligence.py $ARGUMENTS
+   uv run python scripts/feature_intelligence.py $ARGUMENTS
    ```
 
 4. **Report includes:**

package/commands/flashback.md

@@ -1,7 +1,6 @@
 ---
 name: flashback
 description: Session context restoration — "where was I?" summary after days away. Current best, pending hypotheses, last session, annotations.
-disable-model-invocation: true
 argument-hint: "[--days 7] [--last 10]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -9,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Come back to a project after a week and start working in 10 seconds instead of 30 minutes.
 
 ## Steps
-1. **Activate environment:** `source .venv/bin/activate`
-2. **Run:** `python scripts/session_flashback.py $ARGUMENTS`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv run python scripts/session_flashback.py $ARGUMENTS`
 3. **Report:** current best, last session experiments, pending hypotheses, annotations, budget, suggested next action
 4. **Saved output:** `experiments/flashbacks/flashback-*.yaml`
 

package/commands/fork.md

@@ -1,7 +1,6 @@
 ---
 name: fork
 description: Branch an experiment into parallel tracks — run both A and B, report the winner.
-disable-model-invocation: true
 argument-hint: "<exp-id> --branches \"approach A\" \"approach B\" [--auto-promote]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Fork an experiment into parallel branches and compare results.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -22,7 +21,7 @@ Fork an experiment into parallel branches and compare results.
 
 3. **Run fork:**
    ```bash
-   python scripts/fork_experiment.py $ARGUMENTS
+   uv run python scripts/fork_experiment.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/commands/frontier.md

@@ -1,7 +1,6 @@
 ---
 name: frontier
 description: Visualize Pareto frontier across multiple objectives — answers "which model is actually best?" when there are tradeoffs.
-disable-model-invocation: true
 argument-hint: "[--metrics \"accuracy,train_seconds,n_params\"] [--ascii]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Visualize the Pareto frontier across multiple objectives from experiment history
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -22,7 +21,7 @@ Visualize the Pareto frontier across multiple objectives from experiment history
 
 3. **Run Pareto analysis:**
    ```bash
-   python scripts/pareto_frontier.py $ARGUMENTS
+   uv run python scripts/pareto_frontier.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/commands/init.md

@@ -1,7 +1,6 @@
 ---
 name: init
-description: Initialize a new ML project with the Turing autoresearch harness. Scaffolds the full experiment infrastructure — immutable evaluation pipeline, agent-editable training code, structured logging, convergence detection hooks, and a Python virtual environment. Use --plan to generate a research plan.
-disable-model-invocation: true
+description: Initialize a new ML project with the Turing autoresearch harness. Scaffolds the full experiment infrastructure — immutable evaluation pipeline, agent-editable training code, structured logging, convergence detection hooks, and a uv-managed Python environment. Use --plan to generate a research plan.
 argument-hint: "[project_name] [--plan]"
 allowed-tools: Read, Write, Edit, Bash(*), Grep, Glob, WebSearch, WebFetch
 ---
@@ -24,7 +23,7 @@ Ask the user for the following (or accept from `$ARGUMENTS` if provided as JSON)
 Once you have all 6 values, delegate to the unified scaffolding script:
 
 ```bash
-python3 <templates_dir>/scripts/scaffold.py \
+uv run python <templates_dir>/scripts/scaffold.py \
     --project-name "<project_name>" \
     --target-metric "<target_metric>" \
     --metric-direction "<metric_direction>" \
@@ -39,7 +38,7 @@ The scaffold script handles everything in a single atomic operation:
 - Creates data/, experiments/, models/ directories
 - Sets up agent memory at `.claude/agent-memory/ml-researcher-{project_name}/MEMORY.md`
 - Configures Claude Code hooks in `.claude/settings.local.json`
-- Creates Python virtual environment and installs requirements
+- Runs `uv sync` from the ML directory when uv is available
 - Verifies all placeholders were replaced (fails loudly if any remain)
 
 ## Locating Templates
@@ -58,7 +57,7 @@ node_modules/claude-turing/templates/
 Example command:
 
 ```bash
-python3 ~/.claude/commands/turing/templates/scripts/scaffold.py \
+uv run python ~/.claude/commands/turing/templates/scripts/scaffold.py \
     --project-name "<project_name>" \
     --target-metric "<target_metric>" \
     --metric-direction "<metric_direction>" \
@@ -72,7 +71,7 @@ python3 ~/.claude/commands/turing/templates/scripts/scaffold.py \
 
 Report what was created:
 - The separation: READ-ONLY (`prepare.py`, `evaluate.py`) vs AGENT-EDITABLE (`train.py`)
-- Next steps: add data to the configured data source path, run `python prepare.py`, then `/turing:train`
+- Next steps: add data to the configured data source path, run `uv run python prepare.py`, then `/turing:train`
 - The taste-leverage loop: `/turing:try` to inject hypotheses, `/turing:brief` for intelligence reports
 
 ## Research Plan Generation (--plan flag)

package/commands/leak.md

@@ -1,7 +1,6 @@
 ---
 name: leak
 description: Targeted leakage detection — probe for data leakage with single-feature tests, correlation checks, and train/test overlap detection.
-disable-model-invocation: true
 argument-hint: "[--deep] [--features feature_1,feature_2]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Actively probe for data leakage. The #1 cause of "too good to be true" results.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -22,7 +21,7 @@ Actively probe for data leakage. The #1 cause of "too good to be true" results.
 
 3. **Run leakage scan:**
    ```bash
-   python scripts/leakage_detector.py $ARGUMENTS
+   uv run python scripts/leakage_detector.py $ARGUMENTS
    ```
 
 4. **Checks performed:**

package/commands/lit.md

@@ -1,7 +1,6 @@
 ---
 name: lit
 description: Literature search scoped to the current experiment domain — find papers, SOTA baselines, and related work without leaving the terminal.
-disable-model-invocation: true
 argument-hint: "<query> | --baseline | --related <exp-id>"
 allowed-tools: Read, Bash(*), Grep, Glob, WebSearch
 ---
@@ -10,9 +9,9 @@ Search the literature for papers, baselines, and related work.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -24,7 +23,7 @@ Search the literature for papers, baselines, and related work.
 
 3. **Run literature search:**
    ```bash
-   python scripts/literature_search.py $ARGUMENTS
+   uv run python scripts/literature_search.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/commands/logbook.md

@@ -1,9 +1,8 @@
 ---
 name: logbook
 description: Generate a research logbook showing the full experiment narrative — hypotheses proposed, experiments run, decisions made, and progress over time. Outputs HTML (with interactive chart) or markdown.
-disable-model-invocation: true
 argument-hint: "[--since YYYY-MM-DD] [--format html|markdown] [--output path]"
-allowed-tools: Read, Bash(python scripts/*:*, source .venv/bin/activate:*, mkdir:*), Grep, Glob
+allowed-tools: Read, Bash(uv run python scripts/*:*, uv sync:*, mkdir:*), Grep, Glob
 ---
 
 Generate a research logbook that captures the full narrative of the experiment campaign.
@@ -12,7 +11,7 @@ Generate a research logbook that captures the full narrative of the experiment c
 
 1. **Generate the logbook:**
    ```bash
-   source .venv/bin/activate && python scripts/generate_logbook.py
+   uv run python scripts/generate_logbook.py
    ```
 
    **With options from `$ARGUMENTS`:**
@@ -23,13 +22,13 @@ Generate a research logbook that captures the full narrative of the experiment c
    **Common usage:**
    ```bash
    # HTML logbook with interactive trajectory chart
-   source .venv/bin/activate && python scripts/generate_logbook.py --output logbook.html
+   uv run python scripts/generate_logbook.py --output logbook.html
 
    # Markdown for embedding in docs or READMEs
-   source .venv/bin/activate && python scripts/generate_logbook.py --format markdown --output logbook.md
+   uv run python scripts/generate_logbook.py --format markdown --output logbook.md
 
    # Last week's activity
-   source .venv/bin/activate && python scripts/generate_logbook.py --since 2026-03-24 --output logbook.html
+   uv run python scripts/generate_logbook.py --since 2026-03-24 --output logbook.html
    ```
 
 2. **Present the result:**

package/commands/merge.md

@@ -1,7 +1,6 @@
 ---
 name: merge
 description: Model merging — average weights from multiple checkpoints into a single model (soups, TIES, DARE). Free accuracy, zero latency cost.
-disable-model-invocation: true
 argument-hint: "<exp-ids...> [--method uniform|greedy|ties|dare]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,8 +9,8 @@ Combine model weights (not predictions) into a single, better model with no late
 
 ## Steps
 
-1. **Activate environment:** `source .venv/bin/activate`
-2. **Run:** `python scripts/model_merger.py $ARGUMENTS`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv run python scripts/model_merger.py $ARGUMENTS`
 3. **Methods:** uniform soup (simple average), greedy soup (include only if improves), TIES (trim+elect+merge), DARE (drop+rescale)
 4. **Report:** compatibility check, per-model metrics, method comparison, improvement delta
 5. **Saved output:** `experiments/merges/merge-*.yaml`

package/commands/mode.md

@@ -1,7 +1,6 @@
 ---
 name: mode
 description: Set the research strategy mode — explore (try new things), exploit (refine what works), or replicate (verify results). Drives novelty guard policy and agent behavior.
-disable-model-invocation: true
 argument-hint: "<explore|exploit|replicate>"
 ---
 
@@ -21,7 +20,7 @@ Set the research mode for the current project. The mode determines how the novel
 
 2. **Update experiment state:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    python -c "
    import yaml
    from pathlib import Path

package/commands/onboard.md

@@ -1,7 +1,6 @@
 ---
 name: onboard
 description: Project onboarding — generate a walkthrough for new collaborators. Task, history, decisions, next steps.
-disable-model-invocation: true
 argument-hint: "[--audience researcher|engineer|stakeholder] [--depth brief|full]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -9,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 5-minute read that replaces a 1-hour onboarding meeting.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/generate_onboarding.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/generate_onboarding.py $ARGUMENTS`
 3. **Saved:** `ONBOARDING.md`
 
 ## Examples

package/commands/paper.md

@@ -1,7 +1,6 @@
 ---
 name: paper
 description: Draft mechanical paper sections (setup, results, ablation, hyperparameters) from experiment logs. LaTeX and markdown output.
-disable-model-invocation: true
 argument-hint: "[--sections setup,results,ablation] [--format latex|markdown]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Draft paper sections directly from experiment data.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -21,7 +20,7 @@ Draft paper sections directly from experiment data.
 
 3. **Run paper drafting:**
    ```bash
-   python scripts/draft_paper_sections.py $ARGUMENTS
+   uv run python scripts/draft_paper_sections.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/commands/plan.md

@@ -1,7 +1,6 @@
 ---
 name: plan
 description: Research planning assistant — design a strategic experiment campaign with budget-aware ROI allocation.
-disable-model-invocation: true
 argument-hint: "[--budget 20] [--goal \"maximize F1 for production\"]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -9,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Design the next N experiments strategically, not randomly. Allocates budget by expected ROI.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/research_planner.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/research_planner.py $ARGUMENTS`
 3. **Saved:** `experiments/plans/`
 
 ## How it works

package/commands/poster.md

@@ -1,9 +1,8 @@
 ---
 name: poster
 description: Generate a single-page HTML research poster summarizing the experiment campaign — best result, trajectory, key findings, and methodology. Adapted from posterskill's self-contained HTML architecture.
-disable-model-invocation: true
 argument-hint: "[title override]"
-allowed-tools: Read, Write, Edit, Bash(python scripts/*:*, source .venv/bin/activate:*, mkdir:*, open:*), Grep, Glob
+allowed-tools: Read, Write, Edit, Bash(uv run python scripts/*:*, uv sync:*, mkdir:*, open:*), Grep, Glob
 ---
 
 Generate a research poster summarizing the experiment campaign as a single self-contained HTML file. Adapted from [posterskill](https://github.com/ethanweber/posterskill)'s architecture — no build step, works when opened as `file://`.
@@ -16,8 +15,8 @@ Read the experiment history and project context:
 
 ```bash
 cat config.yaml
-source .venv/bin/activate && python scripts/generate_brief.py
-source .venv/bin/activate && python scripts/show_metrics.py --last 20
+uv run python scripts/generate_brief.py
+uv run python scripts/show_metrics.py --last 20
 cat experiment_state.yaml 2>/dev/null || true
 cat RESEARCH_PLAN.md 2>/dev/null || true
 ```

package/commands/postmortem.md

@@ -1,7 +1,6 @@
 ---
 name: postmortem
 description: Failure postmortem — diagnose why experiments stopped improving and get actionable next steps.
-disable-model-invocation: true
 argument-hint: "[--window 10] [--auto-trigger 5]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -9,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 When experiments stop improving, find out why. Diagnoses search space exhaustion, config errors, data issues, metric ceilings, and noise floors.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/failure_postmortem.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/failure_postmortem.py $ARGUMENTS`
 3. **Saved:** `experiments/postmortems/`
 
 ## Diagnosis categories

package/commands/preflight.md

@@ -1,30 +1,29 @@
 ---
 name: preflight
 description: Pre-flight resource check — estimates VRAM, RAM, and disk requirements before running ML training. Compares against available system resources and issues PASS/WARN/FAIL verdict. Use before training to catch OOM errors before they happen.
-disable-model-invocation: true
 argument-hint: "[--model-type torch] [--params 10M] [--batch-size 32]"
-allowed-tools: Read, Bash(python scripts/*:*, source .venv/bin/activate:*, nvidia-smi:*), Grep, Glob
+allowed-tools: Read, Bash(uv run python scripts/*:*, uv sync:*, nvidia-smi:*), Grep, Glob
 ---
 
 Check whether the current system has enough resources to run the planned experiment.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Run preflight check:**
 
    If `$ARGUMENTS` is empty (auto-detect from config.yaml):
    ```bash
-   python scripts/preflight.py
+   uv run python scripts/preflight.py
    ```
 
    If `$ARGUMENTS` contains flags:
    ```bash
-   python scripts/preflight.py $ARGUMENTS
+   uv run python scripts/preflight.py $ARGUMENTS
    ```
 
 3. **Interpret the verdict:**

package/commands/present.md

@@ -1,7 +1,6 @@
 ---
 name: present
 description: Presentation figure generation — training curves, comparison charts, ablation tables, Pareto plots, sensitivity heatmaps.
-disable-model-invocation: true
 argument-hint: "[--figures training,comparison] [--style light|dark|poster]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -9,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Generate presentation-ready figure specifications from experiment data in seconds.
 
 ## Steps
-1. **Activate environment:** `source .venv/bin/activate`
-2. **Run:** `python scripts/generate_figures.py $ARGUMENTS`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv run python scripts/generate_figures.py $ARGUMENTS`
 3. **Figure types:** training, comparison, ablation, pareto, sensitivity
 4. **Styles:** light (papers), dark (demos), poster (large fonts)
 5. **Saved output:** `paper/figures/`

package/commands/profile.md

@@ -1,7 +1,6 @@
 ---
 name: profile
 description: Profile a training run — timing breakdown, memory usage, throughput, bottleneck detection with actionable recommendations.
-disable-model-invocation: true
 argument-hint: "[exp-id] [--seed 42]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Profile a training run to identify performance bottlenecks.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -21,7 +20,7 @@ Profile a training run to identify performance bottlenecks.
 
 3. **Run profiling:**
    ```bash
-   python scripts/profile_training.py $ARGUMENTS
+   uv run python scripts/profile_training.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/commands/prune.md

@@ -1,7 +1,6 @@
 ---
 name: prune
 description: Weight pruning — measure accuracy at different sparsity levels, find the knee point, produce a smaller/faster model.
-disable-model-invocation: true
 argument-hint: "<exp-id> [--sparsity 0.5,0.75,0.9] [--method magnitude|structured|lottery]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,8 +9,8 @@ Remove redundant weights for faster inference and smaller models.
 
 ## Steps
 
-1. **Activate environment:** `source .venv/bin/activate`
-2. **Run:** `python scripts/model_pruning.py $ARGUMENTS`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv run python scripts/model_pruning.py $ARGUMENTS`
 3. **Methods:** magnitude (zero small weights), structured (remove neurons), lottery (iterative with rewind)
 4. **For tree models:** progressively reduces n_estimators
 5. **Report:** sparsity sweep table, knee point, recommended sparsity

package/commands/quantize.md

@@ -1,7 +1,6 @@
 ---
 name: quantize
 description: Post-training quantization — FP32→INT8/FP16, measure accuracy loss, 2-4x speedup with <0.5% accuracy loss.
-disable-model-invocation: true
 argument-hint: "<exp-id> [--precision int8|fp16|dynamic]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,8 +9,8 @@ Quantize for production. Lowest-effort optimization: 2-4x speedup, 2-4x memory r
 
 ## Steps
 
-1. **Activate environment:** `source .venv/bin/activate`
-2. **Run:** `python scripts/model_quantization.py $ARGUMENTS`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv run python scripts/model_quantization.py $ARGUMENTS`
 3. **Precision levels:** FP32 (baseline), FP16 (GPU), INT8 dynamic (simplest), INT8 static (best accuracy)
 4. **Report:** precision comparison table, recommended level, QAT suggestion if needed
 5. **Saved output:** `experiments/quantization/<exp-id>-quantization.yaml`

package/commands/queue.md

@@ -1,7 +1,6 @@
 ---
 name: queue
 description: Queue experiments for batch execution with priority ordering and dependency chains. Load the queue, walk away, read the summary.
-disable-model-invocation: true
 argument-hint: "<add|list|run|pause|clear> [description] [--priority high] [--after q-001]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Manage the experiment queue for unattended batch execution.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -24,7 +23,7 @@ Manage the experiment queue for unattended batch execution.
 
 3. **Run queue manager:**
    ```bash
-   python scripts/experiment_queue.py $ARGUMENTS
+   uv run python scripts/experiment_queue.py $ARGUMENTS
    ```
 
 4. **Report results by action:**

package/commands/registry.md

@@ -1,7 +1,6 @@
 ---
 name: registry
 description: Model registry — track, promote, and govern the model lifecycle from candidate to production.
-disable-model-invocation: true
 argument-hint: "[list|register|promote|demote|archive|history] [exp-id] [stage]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -9,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Track which model is production, staging, candidate, or archived. Promotion requires passing gates.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/model_lifecycle.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/model_lifecycle.py $ARGUMENTS`
 3. **Registry:** `experiments/registry.yaml`
 
 ## Promotion gates

package/commands/regress.md

@@ -1,7 +1,6 @@
 ---
 name: regress
 description: Performance regression gate — re-run best experiment after code/dependency changes and verify metrics haven't degraded.
-disable-model-invocation: true
 argument-hint: "[--tolerance 0.01] [--against exp-id] [--quick]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ CI for your model. After any change to code, dependencies, or data, verify metri
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -24,7 +23,7 @@ CI for your model. After any change to code, dependencies, or data, verify metri
 
 3. **Run regression gate:**
    ```bash
-   python scripts/regression_gate.py $ARGUMENTS
+   uv run python scripts/regression_gate.py $ARGUMENTS
    ```
 
 4. **Report results:**