Skip to content

amazon-science/ammo / ai_cli_session/.codex/skills/ammo

Profile and optimize GPU kernels for vLLM inference on NVIDIA GPUs. Use when targeting a specific model, hardware, dtype, parallelism, and workload to improve latency.

FileKindSize
RUNTIME.mdmarkdown4.9 KB
SKILL.mdskill md18.5 KB
agents/ammo-auditor.mdmarkdown9.1 KB
agents/ammo-champion.mdmarkdown9.6 KB
agents/ammo-delegate.mdmarkdown3.2 KB
agents/ammo-implementer.mdmarkdown13.8 KB
agents/ammo-investigator.mdmarkdown4.0 KB
agents/ammo-report.mdmarkdown2.9 KB
agents/ammo-researcher.mdmarkdown10.3 KB
agents/ammo-resolver.mdmarkdown4.4 KB
agents/ammo-transcript-monitor.mdmarkdown7.8 KB
agents/openai.yamlexecutablescript313 B
data/ATTRIBUTION.mdmarkdown1.4 KB
data/gsm8k_full.jsonexecutablescript735.5 KB
data/gsm8k_subset.jsonexecutablescript116.8 KB
eval/EVAL-SKILL.mdexecutablescript21.8 KB
eval/agents/transcript_grader.mdexecutablescript18.0 KB
eval/causal/__init__.pyexecutablescript137 B
eval/causal/agents/causal_analyzer.mdexecutablescript10.5 KB
eval/causal/build_dag.pyexecutablescript21.6 KB
eval/causal/diff_versions.pyexecutablescript38.5 KB
eval/causal/extract_events.pyexecutablescript36.3 KB
eval/causal/generate_postmortem.pyexecutablescript17.0 KB
eval/causal/score_nodes.pyexecutablescript21.5 KB
eval/causal/templates/narrative_template.mdexecutablescript472 B
eval/causal/templates/viz_template.htmlexecutablescript9.5 KB
eval/causal/tests/__init__.pyexecutablescript151 B
eval/causal/tests/conftest.pyexecutablescript448 B
eval/causal/tests/fixtures/sample_session.jsonlexecutablescript10.4 KB
eval/causal/tests/fixtures/sample_session_data.jsonexecutablescript3.4 KB
eval/causal/tests/fixtures/sample_snapshot.jsonexecutablescript2.5 KB
eval/causal/tests/test_build_dag.pyexecutablescript2.7 KB
eval/causal/tests/test_diff_versions.pyexecutablescript13.5 KB
eval/causal/tests/test_extract_events.pyexecutablescript3.7 KB
eval/causal/tests/test_generate_postmortem.pyexecutablescript3.1 KB
eval/causal/tests/test_score_nodes.pyexecutablescript3.3 KB
eval/scripts/aggregate_versions.pyexecutablescript15.2 KB
eval/scripts/archive_run.pyexecutablescript9.1 KB
eval/scripts/codex_session.pyexecutablescript10.6 KB
eval/scripts/generate_dashboard.pyexecutablescript5.3 KB
eval/scripts/parse_artifacts.pyexecutablescript48.1 KB
eval/scripts/parse_session_logs.pyexecutablescript51.3 KB
eval/scripts/rescore_archived.pyexecutablescript5.5 KB
eval/scripts/score_campaign.pyexecutablescript43.8 KB
eval/scripts/snapshot_changes.pyexecutablescript11.1 KB
eval/scripts/verify_citations.pyexecutablescript8.8 KB
eval/tests/test_dashboard_bugs.pyexecutablescript8.8 KB
eval/tests/test_parse_session_logs.pyexecutablescript3.9 KB
eval/tests/test_parse_session_logs_round_inference.pyexecutablescript11.0 KB
eval/tests/test_score_campaign_diluted.pyexecutablescript9.4 KB
eval/viewer/dashboard_template.htmlexecutablescript15.1 KB
instrumentation/sitecustomize.pyexecutablescript3.6 KB
orchestration/audit-protocol.mdmarkdown9.3 KB
orchestration/debate-protocol.mdmarkdown11.2 KB
orchestration/integration-logic.mdmarkdown10.3 KB
orchestration/parallel-tracks.mdmarkdown8.9 KB
references/artifact-layout.mdexecutablescript22.4 KB
references/audit-invariants.mdmarkdown10.6 KB
references/champion-common-patterns.mdmarkdown3.4 KB
references/crossover-probing.mdexecutablescript4.7 KB
references/cudagraph-safety.mdmarkdown2.7 KB
references/debate-rules.mdmarkdown4.7 KB
references/debate-scoring-rubric.mdexecutablescript16.7 KB
references/e2e-delta-math.mdexecutablescript17.9 KB
references/e2e-latency-guide.mdexecutablescript9.6 KB
references/fusion-feasibility-heuristics.mdmarkdown5.6 KB
references/gpu-pool.mdexecutablescript5.4 KB
references/impl-track-rules.mdexecutablescript13.8 KB
references/nsys-profiling-guide.mdmarkdown9.8 KB
references/optimization-categories.mdexecutablescript11.0 KB
references/shutdown-protocol.mdexecutablescript3.1 KB
references/technology-selection.mdmarkdown5.0 KB
references/torch-compile-contract.mdmarkdown13.8 KB
references/validation-defaults.mdexecutablescript34.2 KB
references/workload-invocation.mdexecutablescript4.9 KB
references/writing-style.mdexecutablescript6.9 KB
scripts/ammo_state.pyexecutablescript142.0 KB
scripts/artifact_layout.jsonconfig16.3 KB
scripts/check_projection_accuracy.pyexecutablescript11.7 KB
scripts/create_evidence_template.pyexecutablescript9.7 KB
scripts/create_worktree_with_build.shexecutablescript10.2 KB
scripts/generate_validation_report.pyexecutablescript35.7 KB
scripts/gpu_reservation.pyexecutablescript27.1 KB
scripts/hook_cmd_classify.pyscript13.3 KB
scripts/mine_trace.pyscript29.4 KB
scripts/monitor_queue_ack.pyexecutablescript6.1 KB
scripts/ncu_sanity.shexecutablescript5.2 KB
scripts/ncu_sanity_driver.pyexecutablescript8.5 KB
scripts/new_target.pyexecutablescript22.0 KB
scripts/preflight_vllm_api.pyexecutablescript12.3 KB
scripts/reconcile_track_state.pyexecutablescript15.8 KB
scripts/remove_worktree_cleanup.shexecutablescript1.1 KB
scripts/resolve_codex_transcript.pyexecutablescript3.6 KB
scripts/run_vllm_bench_latency_sweep.pyexecutablescript249.6 KB
scripts/transcript_filter.pyexecutablescript38.4 KB
scripts/transitions.jsonexecutablescript1.5 KB
scripts/verify_validation_gates.pyexecutablescript88.8 KB
tests/agents/test-champion.mdexecutablescript20.4 KB
tests/agents/test-impl-champion.mdexecutablescript14.3 KB
tests/agents/test-implementer.mdexecutablescript15.8 KB
tests/agents/test-orchestrator.mdexecutablescript33.8 KB
tests/agents/test-researcher.mdexecutablescript21.0 KB
tests/agents/test-transcript-monitor.mdexecutablescript13.4 KB
tests/fixtures/diluted_pass/legacy_no_phase.golden.mdmarkdown1.1 KB
tests/fixtures/diluted_pass/legacy_no_phase.golden.summary.jsonconfig582 B
tests/fixtures/diluted_pass/legacy_no_phase.jsonconfig400 B
tests/fixtures/diluted_pass/legacy_scalar_phase.golden.mdmarkdown2.0 KB
tests/fixtures/diluted_pass/legacy_scalar_phase.golden.summary.jsonconfig1.0 KB
tests/fixtures/diluted_pass/legacy_scalar_phase.jsonconfig626 B
tests/fixtures/mining/real_campaign_bottleneck_analysis.mdmarkdown20.7 KB
tests/run_all.shexecutablescript1.6 KB
tests/scripts/test_transcript_filter.pyexecutablescript41.1 KB
tests/test_agent_runtime_contracts.pyexecutablescript1.8 KB
tests/test_ammo_state.pyexecutablescript71.7 KB
tests/test_artifact_layout_manifest.pyscript11.6 KB
tests/test_audit_started.pyscript18.2 KB
tests/test_correctness_comparator.pyscript12.6 KB
tests/test_diluted_pass.pyscript24.4 KB
tests/test_drift_compat.pyscript5.1 KB
tests/test_evidence_freshness.pyexecutablescript5.6 KB
tests/test_fail_closed.pyexecutablescript14.7 KB
tests/test_gpu_reservation.pyexecutablescript24.8 KB
tests/test_gpu_reservation_session_id.pyexecutablescript11.2 KB
tests/test_guidance_semantic_contract.pyscript24.9 KB
tests/test_hook_cmd_classify_parity.pyscript11.7 KB
tests/test_hook_semantics.pyexecutablescript95.3 KB
tests/test_mine_trace.pyscript24.2 KB
tests/test_mining_invalidated_schema.pyexecutablescript9.4 KB
tests/test_new_target_dp_ep.pyexecutablescript7.4 KB
tests/test_new_target_v2_scaffold.pyexecutablescript13.1 KB
tests/test_parse_artifacts.pyexecutablescript3.0 KB
tests/test_policy_convergence.pyscript797 B
tests/test_preflight_vllm_api.pyscript13.3 KB
tests/test_projection_accuracy_v2.pyexecutablescript4.1 KB
tests/test_reconcile_track_state.pyexecutablescript18.2 KB
tests/test_resolve_codex_transcript.pyexecutablescript3.1 KB
tests/test_state_schema_semantics.pyexecutablescript7.6 KB
tests/test_status_set_sync.pyexecutablescript9.1 KB
tests/test_sweep_baseline_from_arm.pyscript11.0 KB
tests/test_sweep_decode_capture.pyexecutablescript31.8 KB
tests/test_sweep_dp.pyexecutablescript45.4 KB
tests/test_sweep_fresh_cache.pyscript5.5 KB
tests/test_sweep_profiler_guard.pyscript22.6 KB
tests/test_sweep_real_prompts.pyscript20.1 KB
tests/test_sweep_refactor.pyexecutablescript37.6 KB
tests/test_sweep_round_slot.pyexecutablescript7.4 KB
tests/test_validation_report_phase_triage.pyexecutablescript10.0 KB
tests/test_validation_report_v2.pyexecutablescript6.2 KB
tests/test_verify_validation_gates.pyexecutablescript52.9 KB
tests/test_workload_matrix.pyexecutablescript19.3 KB

tests/test_new_target_v2_scaffold.py

View on GitHub
#!/usr/bin/env python3
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: CC-BY-NC-4.0
"""Regression tests for round-scoped new_target.py scaffold."""

from __future__ import annotations

import json
import importlib.util
import os
import subprocess
import sys
from pathlib import Path

import pytest


_SCRIPTS_DIR = Path(__file__).resolve().parent.parent / "scripts"
_NEW_TARGET = _SCRIPTS_DIR / "new_target.py"
_SCHEMA = Path(__file__).resolve().parents[3] / "schemas" / "state.schema.json"
_spec = importlib.util.spec_from_file_location("new_target", str(_NEW_TARGET))
new_target = importlib.util.module_from_spec(_spec)
sys.modules["new_target"] = new_target
_spec.loader.exec_module(new_target)


@pytest.fixture
def scaffolded_artifact_dir(tmp_path: Path) -> Path:
    artifact_dir = tmp_path / "artifact"
    cmd = [
        sys.executable,
        str(_NEW_TARGET),
        "--artifact-dir", str(artifact_dir),
        "--model-id", "test-model",
        "--hardware", "H100",
        "--dtype", "fp8",
        "--tp", "1",
    ]
    result = subprocess.run(cmd, capture_output=True, text=True)
    assert result.returncode == 0, f"new_target.py failed: {result.stdout} / {result.stderr}"
    return artifact_dir


def test_scaffold_emits_schema_4_1(scaffolded_artifact_dir: Path):
    state = json.loads((scaffolded_artifact_dir / "state.json").read_text(encoding="utf-8"))

    assert state["campaign"]["schema_version"] == "4.2"


def test_state_schema_defines_v4_1_contract_blocks():
    schema = json.loads(_SCHEMA.read_text(encoding="utf-8"))
    campaign = schema["properties"]["campaign"]["properties"]
    config = campaign["config"]["properties"]

    assert "4.1" in campaign["schema_version"]["enum"]
    assert "optimization_category" in schema["$defs"]
    assert schema["$defs"]["optimization_category"]["enum"] == [
        "kernel_replacement",
        "kernel_fusion",
        "dispatch_optimization",
        "custom_kernel",
        "weight_layout_transform",
        "compute_graph_pass",
        "execution_pipeline_restructuring",
        "communication_strategy",
        "attention_kv_layout",
    ]
    assert config["min_e2e_improvement_pct"]["default"] == 0.5
    assert "lossless_e2e_deflation_factor" not in config
    assert "lossy_quant_e2e_deflation_factor" not in config
    assert "ceiling_detection" not in config
    assert "decision_tree" not in config
    assert "routing_recommendation" not in config


def test_scaffold_uses_current_min_e2e_default_without_deflation(scaffolded_artifact_dir: Path):
    state = json.loads((scaffolded_artifact_dir / "state.json").read_text(encoding="utf-8"))

    config = state["campaign"]["config"]
    assert config["min_e2e_improvement_pct"] == 0.5
    assert "lossless_e2e_deflation_factor" not in config
    assert "lossy_quant_e2e_deflation_factor" not in config


def test_target_json_carries_schema_derived_minimum(scaffolded_artifact_dir: Path):
    target = json.loads((scaffolded_artifact_dir / "target.json").read_text(encoding="utf-8"))

    assert target["gating"]["min_e2e_improvement_pct"] == 0.5


def test_scaffold_freezes_max_num_seqs_and_multi_workload(tmp_path: Path):
    artifact_dir = tmp_path / "matrix"
    result = subprocess.run(
        [
            sys.executable,
            str(_NEW_TARGET),
            "--artifact-dir",
            str(artifact_dir),
            "--model-id",
            "test-model",
            "--batch-sizes",
            "1",
            "8",
            "--isl-osl",
            "64:512,2048:256",
            "--max-num-seqs",
            "32",
        ],
        capture_output=True,
        text=True,
    )

    assert result.returncode == 0, result.stderr
    target = json.loads((artifact_dir / "target.json").read_text(encoding="utf-8"))
    assert target["bench"]["extra_args"][-2:] == ["--max-num-seqs", "32"]
    assert target["workload"]["workload_matrix"] == [
        {"input_len": 64, "output_len": 512, "batch_size": 1},
        {"input_len": 64, "output_len": 512, "batch_size": 8},
        {"input_len": 2048, "output_len": 256, "batch_size": 1},
        {"input_len": 2048, "output_len": 256, "batch_size": 8},
    ]


def test_scaffold_rejects_unresolved_auto_before_writing(tmp_path: Path):
    artifact_dir = tmp_path / "auto"
    result = subprocess.run(
        [
            sys.executable,
            str(_NEW_TARGET),
            "--artifact-dir",
            str(artifact_dir),
            "--model-id",
            "definitely-not-cached/model",
            "--max-model-len",
            "auto",
        ],
        capture_output=True,
        text=True,
    )

    assert result.returncode != 0
    assert "supply the concrete model limit" in result.stderr
    assert not (artifact_dir / "state.json").exists()


def test_programmatic_state_and_target_use_same_target_fields_threshold(tmp_path: Path):
    fields = new_target.TargetFields(
        model_id="model",
        hardware="H100",
        dtype="fp8",
        tp=1,
        ep=1,
        max_model_len=4096,
        input_len=64,
        output_len=128,
        batch_sizes=[1, 8],
        num_iters=10,
        noise_tolerance_pct=0.75,
        catastrophic_regression_pct=4.0,
        min_e2e_improvement_pct=1.25,
    )

    state = new_target._state_json(fields, tmp_path)
    target = new_target._target_json(fields, tmp_path)

    assert state["campaign"]["config"]["min_e2e_improvement_pct"] == 1.25
    assert target["gating"]["min_e2e_improvement_pct"] == 1.25


def test_scaffold_rejects_schema_invalid_threshold_before_writing(tmp_path: Path):
    artifact_dir = tmp_path / "invalid"

    result = subprocess.run(
        [
            sys.executable,
            str(_NEW_TARGET),
            "--artifact-dir",
            str(artifact_dir),
            "--min-e2e-improvement",
            "-1",
        ],
        capture_output=True,
        text=True,
    )

    assert result.returncode != 0
    assert "violates schema" in result.stderr
    assert not (artifact_dir / "state.json").exists()


def test_scaffold_uses_claude_num_iters_default(scaffolded_artifact_dir: Path):
    target = json.loads((scaffolded_artifact_dir / "target.json").read_text(encoding="utf-8"))

    assert target["workload"]["num_iters"] == 10


def test_scaffold_creates_rounds_1_dir(scaffolded_artifact_dir: Path):
    assert (scaffolded_artifact_dir / "rounds" / "1").is_dir()


def test_scaffold_creates_profiling_subdirs(scaffolded_artifact_dir: Path):
    base = scaffolded_artifact_dir / "rounds" / "1" / "profiling"
    for sub in ("nsys", "ncu"):
        assert (base / sub).is_dir(), f"missing rounds/1/profiling/{sub}/"
    assert not (base / "probe").exists()
    assert not (base / "torch_profile").exists()


def test_scaffold_creates_sweeps_subdirs(scaffolded_artifact_dir: Path):
    sweeps = scaffolded_artifact_dir / "rounds" / "1" / "sweeps"
    for sub in ("json", "logs", "status"):
        assert (sweeps / "baseline" / sub).is_dir(), f"missing baseline/{sub}/"
    for slot in ("opt", "integration", "golden_capture"):
        assert (sweeps / slot).is_dir(), f"missing sweeps/{slot}/"


def test_scaffold_creates_debate_subdirs(scaffolded_artifact_dir: Path):
    base = scaffolded_artifact_dir / "rounds" / "1" / "debate"
    for sub in ("proposals", "micro_experiments", "monitor_audits"):
        assert (base / sub).is_dir(), f"missing debate/{sub}/"


def test_scaffold_creates_round_scoped_work_dirs(scaffolded_artifact_dir: Path):
    for sub in ("mining", "tracks", "audits", "_archive"):
        assert (scaffolded_artifact_dir / "rounds" / "1" / sub).is_dir()


def test_scaffold_creates_blockers_at_root(scaffolded_artifact_dir: Path):
    assert (scaffolded_artifact_dir / "blockers").is_dir()
    assert not (scaffolded_artifact_dir / "rounds" / "1" / "blockers").exists()


def test_scaffold_no_legacy_dirs(scaffolded_artifact_dir: Path):
    for legacy in ("investigation", "runs", "nsys", "e2e_latency", "monitoring", "tracks", "debate", "mining", "audits"):
        assert not (scaffolded_artifact_dir / legacy).exists(), (
            f"legacy root dir {legacy}/ should not be scaffolded"
        )


def test_no_constraints_md_at_root(scaffolded_artifact_dir: Path):
    assert not (scaffolded_artifact_dir / "constraints.md").exists()


def _run_new_target(artifact_dir: Path, extra_args: list[str], env: dict[str, str] | None = None):
    cmd = [
        sys.executable,
        str(_NEW_TARGET),
        "--artifact-dir", str(artifact_dir),
        "--model-id", "test-model",
        "--hardware", "H100",
        "--dtype", "fp8",
        "--tp", "1",
        *extra_args,
    ]
    return subprocess.run(cmd, capture_output=True, text=True, env=env)


def test_scaffold_all_flags_emits_no_placeholder(tmp_path: Path):
    artifact_dir = tmp_path / "full"
    result = _run_new_target(artifact_dir, ["--gpu-model", "NVIDIA H100 80GB HBM3"])

    assert result.returncode == 0, result.stderr
    state_text = (artifact_dir / "state.json").read_text(encoding="utf-8")
    assert "<FILL_ME>" not in state_text
    state = json.loads(state_text)
    assert state["gpu_resources"]["gpu_model"] == "NVIDIA H100 80GB HBM3"


def test_scaffold_detects_gpu_model_from_nvidia_smi(tmp_path: Path):
    fake_bin = tmp_path / "bin"
    fake_bin.mkdir()
    fake_smi = fake_bin / "nvidia-smi"
    fake_smi.write_text("#!/bin/sh\necho 'NVIDIA L40S'\n", encoding="utf-8")
    fake_smi.chmod(0o755)
    env = dict(os.environ)
    env["PATH"] = f"{fake_bin}:{env.get('PATH', '')}"

    artifact_dir = tmp_path / "detected"
    result = _run_new_target(artifact_dir, [], env=env)

    assert result.returncode == 0, result.stderr
    state_text = (artifact_dir / "state.json").read_text(encoding="utf-8")
    assert "<FILL_ME>" not in state_text
    state = json.loads(state_text)
    assert state["gpu_resources"]["gpu_model"] == "NVIDIA L40S"


def test_scaffold_warns_and_keeps_placeholder_without_detection(tmp_path: Path):
    empty_bin = tmp_path / "emptybin"
    empty_bin.mkdir()
    env = dict(os.environ)
    env["PATH"] = str(empty_bin)

    artifact_dir = tmp_path / "undetected"
    result = _run_new_target(artifact_dir, [], env=env)

    assert result.returncode == 0, result.stderr
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))
    assert state["gpu_resources"]["gpu_model"] == "<FILL_ME>"
    assert "gpu_model" in result.stderr
    assert "WARNING" in result.stderr


def test_scaffold_detection_scopes_query_to_cuda_visible_devices(tmp_path: Path):
    # nvidia-smi ignores CUDA_VISIBLE_DEVICES, so on a heterogeneous host an
    # unscoped query names a GPU the session does not own. The fake below
    # models GPU0/1 = A100, GPU2/3 = H100 and honors -i scoping.
    fake_bin = tmp_path / "bin"
    fake_bin.mkdir()
    fake_smi = fake_bin / "nvidia-smi"
    fake_smi.write_text(
        "#!/bin/sh\n"
        'case "$*" in\n'
        '  *"-i 2,3"*) echo "NVIDIA H100 80GB HBM3"; echo "NVIDIA H100 80GB HBM3";;\n'
        '  *"-i"*) echo "bad device index" >&2; exit 6;;\n'
        '  *) echo "NVIDIA A100-SXM4-40GB"; echo "NVIDIA A100-SXM4-40GB";\n'
        '     echo "NVIDIA H100 80GB HBM3"; echo "NVIDIA H100 80GB HBM3";;\n'
        "esac\n",
        encoding="utf-8",
    )
    fake_smi.chmod(0o755)
    env = dict(os.environ)
    env["PATH"] = f"{fake_bin}:{env.get('PATH', '')}"
    env["CUDA_VISIBLE_DEVICES"] = "2,3"

    artifact_dir = tmp_path / "scoped"
    result = _run_new_target(artifact_dir, [], env=env)

    assert result.returncode == 0, result.stderr
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))
    assert state["gpu_resources"]["gpu_model"] == "NVIDIA H100 80GB HBM3"


def test_scaffold_bad_visible_devices_falls_back_to_placeholder(tmp_path: Path):
    # A CVD the driver rejects must fail closed to the placeholder (caught by
    # verify_validation_gates.py), never to a confidently-wrong model name.
    fake_bin = tmp_path / "bin"
    fake_bin.mkdir()
    fake_smi = fake_bin / "nvidia-smi"
    fake_smi.write_text(
        "#!/bin/sh\n"
        'case "$*" in\n'
        '  *"-i"*) echo "No devices were found" >&2; exit 6;;\n'
        '  *) echo "NVIDIA A100-SXM4-40GB";;\n'
        "esac\n",
        encoding="utf-8",
    )
    fake_smi.chmod(0o755)
    env = dict(os.environ)
    env["PATH"] = f"{fake_bin}:{env.get('PATH', '')}"
    env["CUDA_VISIBLE_DEVICES"] = "99"

    artifact_dir = tmp_path / "badcvd"
    result = _run_new_target(artifact_dir, [], env=env)

    assert result.returncode == 0, result.stderr
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))
    assert state["gpu_resources"]["gpu_model"] == "<FILL_ME>"
    assert "WARNING" in result.stderr


def test_scaffold_whitespace_gpu_model_flag_falls_through(tmp_path: Path):
    empty_bin = tmp_path / "emptybin"
    empty_bin.mkdir()
    env = dict(os.environ)
    env["PATH"] = str(empty_bin)

    artifact_dir = tmp_path / "wsflag"
    result = _run_new_target(artifact_dir, ["--gpu-model", "   "], env=env)

    assert result.returncode == 0, result.stderr
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))
    assert state["gpu_resources"]["gpu_model"] == "<FILL_ME>"
    assert "WARNING" in result.stderr
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall