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

eval/scripts/rescore_archived.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
"""Re-score all archived AMMO eval runs using the current scoring logic.

Reads each archived run's snapshot (artifacts_snapshot.json) and optional
transcript grading, re-runs score_campaign.compute_scorecard(), and overwrites
the scorecard.json and report.md in place.

This is used after scoring logic changes (e.g., adding accuracy verification
penalties) to retroactively update all historical scores.

Usage:
  python rescore_archived.py --repository ~/.codex/ammo-eval
  python rescore_archived.py --repository ~/.codex/ammo-eval --dry-run
  python rescore_archived.py --repository ~/.codex/ammo-eval --target qwen3-5-4b_l40s_bf16_tp1
"""

from __future__ import annotations

import argparse
import json
import sys
from pathlib import Path
from typing import Optional

from score_campaign import compute_scorecard, generate_report


def rescore_run(run_dir: Path, dry_run: bool = False) -> Optional[dict]:
    """Re-score a single archived run. Returns summary dict or None on skip."""
    snapshot_path = run_dir / "artifacts_snapshot.json"
    if not snapshot_path.exists():
        # Some older archives use different names
        for alt in ["snapshot.json"]:
            alt_path = run_dir / alt
            if alt_path.exists():
                snapshot_path = alt_path
                break
        else:
            return None

    snapshot = json.loads(snapshot_path.read_text(encoding="utf-8"))

    # Load transcript grading if available
    transcript_grading = None
    tg_path = run_dir / "transcript_grading.json"
    if tg_path.exists():
        transcript_grading = json.loads(tg_path.read_text(encoding="utf-8"))

    # Read old score for comparison
    old_scorecard_path = run_dir / "scorecard.json"
    old_score = None
    if old_scorecard_path.exists():
        old_sc = json.loads(old_scorecard_path.read_text(encoding="utf-8"))
        old_score = old_sc.get("overall_score")

    # Re-score
    new_scorecard = compute_scorecard(snapshot, transcript_grading)
    new_report = generate_report(new_scorecard, snapshot)
    new_score = new_scorecard.get("overall_score")

    result = {
        "run_dir": str(run_dir),
        "old_score": old_score,
        "new_score": new_score,
        "delta": round(new_score - old_score, 2) if old_score is not None and new_score is not None else None,
        "accuracy_verification": new_scorecard.get("accuracy_verification"),
    }

    if not dry_run:
        old_scorecard_path.write_text(
            json.dumps(new_scorecard, indent=2) + "\n", encoding="utf-8"
        )
        report_path = run_dir / "report.md"
        report_path.write_text(new_report, encoding="utf-8")

    return result


def main() -> int:
    parser = argparse.ArgumentParser(
        description=__doc__,
        formatter_class=argparse.RawDescriptionHelpFormatter,
    )
    parser.add_argument(
        "--repository", type=str, default="~/.codex/ammo-eval",
        help="Path to eval repository (default: ~/.codex/ammo-eval)",
    )
    parser.add_argument(
        "--target", type=str, default=None,
        help="Only re-score runs for this target slug (e.g., qwen3-5-4b_l40s_bf16_tp1)",
    )
    parser.add_argument(
        "--dry-run", action="store_true",
        help="Compute new scores but don't write files",
    )

    args = parser.parse_args()
    repo = Path(args.repository).expanduser().resolve()

    if not repo.exists():
        print(f"ERROR: Repository not found: {repo}", file=sys.stderr)
        return 1

    versions_dir = repo / "versions"
    if not versions_dir.exists():
        print(f"ERROR: No versions directory: {versions_dir}", file=sys.stderr)
        return 1

    results = []
    for version_dir in sorted(versions_dir.iterdir()):
        if not version_dir.is_dir():
            continue
        runs_dir = version_dir / "runs"
        if not runs_dir.exists():
            continue

        for target_dir in sorted(runs_dir.iterdir()):
            if not target_dir.is_dir():
                continue
            if args.target and target_dir.name != args.target:
                continue

            for run_dir in sorted(target_dir.iterdir()):
                if not run_dir.is_dir():
                    continue
                result = rescore_run(run_dir, dry_run=args.dry_run)
                if result:
                    results.append(result)

    # Print summary
    action = "Would re-score" if args.dry_run else "Re-scored"
    print(f"\n{action} {len(results)} run(s):\n")
    print(f"{'Old':>7}  {'New':>7}  {'Delta':>7}  {'Unverified':>10}  Path")
    print("-" * 90)
    for r in results:
        old = f"{r['old_score']:.2f}" if r['old_score'] is not None else "  N/A"
        new = f"{r['new_score']:.2f}" if r['new_score'] is not None else "  N/A"
        delta = f"{r['delta']:+.2f}" if r['delta'] is not None else "  N/A"
        av = r.get("accuracy_verification") or {}
        unverified = av.get("lossy_unverified", 0)
        unv_str = f"{unverified}" if unverified > 0 else "-"
        # Shorten path for display
        short_path = str(r['run_dir']).replace(str(repo) + "/", "")
        print(f"{old:>7}  {new:>7}  {delta:>7}  {unv_str:>10}  {short_path}")

    # Summary stats
    adjusted = [r for r in results if (r.get("accuracy_verification") or {}).get("has_unverified_lossy")]
    print(f"\n{len(adjusted)} run(s) had unverified lossy ops and were adjusted.")

    return 0


if __name__ == "__main__":
    sys.exit(main())
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