Skip to content

alexgreensh/repo-forensics / skills/repo-forensics

repo-forensics

Flagged

Security forensics for git repos, AI skills, and MCP servers. Audits dependencies, detects prompt injection, credential theft, runtime dynamism, manifest drift, known CVEs, CISA KEV (actively exploited) vulns, and 2026 attack patterns. Not for fixing vulnerabilities or pentesting.

FileKindSize
.gitignoreother193 B
SKILL.mdskill md43.4 KB
checksums.jsonconfig10.8 KB
checksums.json.sigother64 B
data/README.mdmarkdown1.3 KB
data/compromised_versions.jsonconfig188.3 KB
data/rule_ids.csvother35.3 KB
data/rulepacks/.gitkeepother221 B
data/rulepacks/dead_anchors.jsonconfig9.0 KB
data/rulepacks/mcp_security.jsonconfig31.2 KB
data/rulepacks/runtime_dynamism.jsonconfig46.7 KB
data/rulepacks/sast.jsonconfig107.6 KB
data/rulepacks/secrets.jsonconfig30.4 KB
data/rulepacks/shared.jsonconfig4.4 KB
data/rulepacks/skill_threats.jsonconfig95.4 KB
data/runtime_floors.jsonconfig2.3 KB
data/yara/cryptominers.yarother1.8 KB
data/yara/hacktools.yarother2.2 KB
data/yara/malware.yarother2.2 KB
data/yara/manifest.jsonconfig8.0 KB
data/yara/webshells.yarother2.5 KB
references/cursor-hook-contract.mdmarkdown5.6 KB
references/kernel_privesc_sandbox_pack.mdmarkdown5.0 KB
references/mcp-attack-patterns.mdmarkdown8.7 KB
references/research_sources.mdmarkdown8.0 KB
references/threat_patterns.mdmarkdown20.3 KB
scripts/_context_gate.pyscript21.7 KB
scripts/_ed25519.pyscript5.1 KB
scripts/_pyc_unmarshal.pyscript17.1 KB
scripts/_shared_patterns.pyscript4.8 KB
scripts/adjudication.pyscript16.4 KB
scripts/adjudication_bridge.pyscript1.0 KB
scripts/aggregate_json.pyscript69.2 KB
scripts/auto_scan.pyexecutablescript152.1 KB
scripts/corpus_sync.pyscript10.0 KB
scripts/cursor_pre_scan.pyscript22.5 KB
scripts/dast_sandbox.sbother1.6 KB
scripts/dead_anchors_extract.pyscript14.8 KB
scripts/dead_anchors_probe.pyscript27.1 KB
scripts/forensics_core.pyscript176.5 KB
scripts/gen_rule_ids.pyscript8.6 KB
scripts/hook_adapter.pyscript19.4 KB
scripts/ioc_manager.pyscript49.6 KB
scripts/parse_pnpm_lock.pyscript7.9 KB
scripts/pre_scan.pyscript143.5 KB
scripts/pypi_pins.pyscript8.1 KB
scripts/refresh_controller.pyexecutablescript48.4 KB
scripts/refresh_threat_dbs.pyexecutablescript19.4 KB
scripts/rule_loader.pyscript44.8 KB
scripts/rulepack_feed.pyscript26.4 KB
scripts/run_forensics.shexecutablescript20.3 KB
scripts/sarif_export.pyscript18.6 KB
scripts/scan_agent_skills.pyscript33.2 KB
scripts/scan_archive.pyscript29.1 KB
scripts/scan_ast.pyscript44.9 KB
scripts/scan_binary.pyscript10.9 KB
scripts/scan_bytecode.pyscript28.2 KB
scripts/scan_dast.pyscript28.8 KB
scripts/scan_dataflow.pyscript15.4 KB
scripts/scan_dead_anchors.pyscript15.9 KB
scripts/scan_decode.pyscript37.5 KB
scripts/scan_dependencies.pyscript124.5 KB
scripts/scan_devcontainer.pyscript8.5 KB
scripts/scan_entropy.pyscript15.6 KB
scripts/scan_entrypoint.pyscript34.3 KB
scripts/scan_git_config.pyscript96.3 KB
scripts/scan_git_forensics.pyscript24.1 KB
scripts/scan_history.pyscript14.5 KB
scripts/scan_infra.pyscript54.3 KB
scripts/scan_integrity.pyscript41.0 KB
scripts/scan_lifecycle.pyscript65.1 KB
scripts/scan_manifest_drift.pyscript47.0 KB
scripts/scan_mcp_security.pyscript42.3 KB
scripts/scan_oversize.pyscript11.7 KB
scripts/scan_post_incident.pyscript36.9 KB
scripts/scan_provenance.pyscript19.4 KB
scripts/scan_runtime_dynamism.pyscript23.5 KB
scripts/scan_runtime_floors.pyscript33.5 KB
scripts/scan_sast.pyscript59.1 KB
scripts/scan_secrets.pyscript11.9 KB
scripts/scan_skill_threats.pyscript102.4 KB
scripts/scan_splitstream.pyscript29.5 KB
scripts/scan_yara.pyscript19.7 KB
scripts/session_scan.pyscript54.1 KB
scripts/suppressions.pyscript15.4 KB
scripts/validate_manifests.pyscript13.7 KB
scripts/verify_install.pyscript26.2 KB
scripts/vuln_feed.pyscript31.1 KB
tests/conftest.pyscript13.4 KB
tests/corpus/DEAD_ANCHORS_CORPUS.mdmarkdown2.3 KB
tests/corpus/budgets.jsonconfig5.6 KB
tests/cursor_helpers.pyscript12.6 KB
tests/fixtures/legacy_main_blocks.jsonconfig10.3 KB
tests/fixtures/powershell_verdict_corpus.jsonconfig114.9 KB
tests/golden/parity_mcp_security.jsonconfig17.5 KB
tests/golden/parity_runtime_dynamism.jsonconfig31.7 KB
tests/golden/parity_sast.jsonconfig59.8 KB
tests/golden/parity_secrets.jsonconfig18.8 KB
tests/golden/parity_skill_threats.jsonconfig48.8 KB
tests/parity_corpus.pyscript6.3 KB
tests/powershell_hook.pyscript8.2 KB
tests/report_builders.pyscript5.0 KB
tests/schemas/sarif-schema-2.1.0.jsonconfig109.1 KB
tests/shell_compat.pyscript2.2 KB
tests/test_adjudication_bridge.pyscript832 B
tests/test_adjudication_containment.pyscript1.4 KB
tests/test_adjudication_output.pyscript20.0 KB
tests/test_adjudication_suppressions.pyscript18.7 KB
tests/test_advisory_adjudication.pyscript1.3 KB
tests/test_agent_relay_rules.pyscript7.8 KB
tests/test_aggregate_json.pyscript10.0 KB
tests/test_auto_scan_patterns.pyscript10.5 KB
tests/test_benign_corpus.pyscript16.4 KB
tests/test_benign_new_scanners.pyscript6.1 KB
tests/test_build_output_skip.pyscript10.6 KB
tests/test_capability_ledger.pyscript18.8 KB
tests/test_codex_install.pyscript10.0 KB
tests/test_codex_marketplace.pyscript3.3 KB
tests/test_comment_false_positives.pyscript2.2 KB
tests/test_composer_dependencies.pyscript4.0 KB
tests/test_compromised_versions.pyscript51.2 KB
tests/test_context_gate.pyscript32.4 KB
tests/test_coverage_status.pyscript7.6 KB
tests/test_css_compounding_shrink.pyscript20.8 KB
tests/test_cursor_adapter.pyscript7.8 KB
tests/test_cursor_benign.pyscript3.4 KB
tests/test_cursor_degrade.pyscript12.7 KB
tests/test_cursor_install.pyscript17.1 KB
tests/test_cursor_latency.pyscript7.2 KB
tests/test_cursor_parity.pyscript5.8 KB
tests/test_cursor_redteam_fn.pyscript4.9 KB
tests/test_cursor_tamper_modify.pyscript14.2 KB
tests/test_cursor_wiring.pyscript32.3 KB
tests/test_d1_yara_correlation.pyscript9.2 KB
tests/test_dead_anchors_extract.pyscript7.6 KB
tests/test_dead_anchors_probe.pyscript19.7 KB
tests/test_evidence_engine_parity.pyscript8.1 KB
tests/test_evidence_model.pyscript11.4 KB
tests/test_forensics_core.pyscript79.2 KB
tests/test_fp_hardening_r3.pyscript9.7 KB
tests/test_fp_hardening_r4.pyscript18.8 KB
tests/test_fp_regression_pairs.pyscript62.5 KB
tests/test_fp_structural.pyscript21.2 KB
tests/test_freshness.pyscript6.2 KB
tests/test_frontmatter_validity.pyscript7.0 KB
tests/test_gpg_rce_hotfix.pyscript4.8 KB
tests/test_hook_inert_data.pyscript6.1 KB
tests/test_hook_scripts.pyscript14.0 KB
tests/test_inspection_cpu_budget.pyscript11.6 KB
tests/test_ioc_manager.pyscript55.4 KB
tests/test_kernel_privesc_rules.pyscript27.8 KB
tests/test_legit_precision_regressions.pyscript6.8 KB
tests/test_lethal_trifecta.pyscript20.7 KB
tests/test_manifest_signature.pyscript1.5 KB
tests/test_manifest_validity.pyscript2.9 KB
tests/test_monotonic_trust_e2e.pyscript4.4 KB
tests/test_non_breaking_contract.pyscript22.7 KB
tests/test_openclaw_install.pyscript6.6 KB
tests/test_pack_parity.pyscript24.8 KB
tests/test_parse_pnpm_lock.pyscript10.7 KB
tests/test_plugin_checkout_provenance.pyscript11.1 KB
tests/test_powershell_hook_wire.pyscript10.6 KB
tests/test_powershell_verdict_corpus.pyscript6.2 KB
tests/test_pr44_hardening.pyscript6.5 KB
tests/test_pre_scan.pyscript19.6 KB
tests/test_pre_scan_composer.pyscript7.4 KB
tests/test_precondition_fields.pyscript4.6 KB
tests/test_provenance_offline.pyscript2.5 KB
tests/test_published_rulepack_feed_current.pyscript1.4 KB
tests/test_py38_compat.pyscript3.3 KB
tests/test_pypi_pinned_versions.pyscript19.3 KB
tests/test_pyproject_string_forms.pyscript2.2 KB
tests/test_redteam_fn_regression.pyscript32.5 KB
tests/test_reflective_fetch_execute.pyscript23.5 KB
tests/test_reflective_review_fixes.pyscript17.8 KB
tests/test_refresh_controller.pyscript19.9 KB
tests/test_refresh_rulepacks.pyscript12.4 KB
tests/test_review_gate_regressions.pyscript9.3 KB
tests/test_rule_loader.pyscript23.2 KB
tests/test_rulepack_feed.pyscript38.1 KB
tests/test_run_forensics_json.pyscript1012 B
tests/test_run_scanner_fail_loud.pyscript6.5 KB
tests/test_runtime_floors.pyscript19.8 KB
tests/test_sandbox_probing_rules.pyscript9.6 KB
tests/test_sarif_export.pyscript19.9 KB
tests/test_scan_agent_skills.pyscript31.3 KB
tests/test_scan_archive.pyscript11.6 KB
tests/test_scan_ast.pyscript12.8 KB
tests/test_scan_binary.pyscript15.3 KB
tests/test_scan_bytecode.pyscript21.5 KB
tests/test_scan_dast.pyscript32.1 KB
tests/test_scan_dataflow.pyscript7.1 KB
tests/test_scan_dead_anchors.pyscript11.5 KB
tests/test_scan_decode.pyscript28.0 KB
tests/test_scan_dependencies.pyscript37.8 KB
tests/test_scan_devcontainer.pyscript8.5 KB
tests/test_scan_entropy.pyscript11.2 KB
tests/test_scan_entrypoint.pyscript19.5 KB
tests/test_scan_git_config.pyscript58.5 KB
tests/test_scan_git_config_review_fixes.pyscript33.3 KB

scripts/validate_manifests.py

View on GitHub
#!/usr/bin/env python3
"""Validate plugin and marketplace manifests before they are shipped."""

import argparse
import json
import re
import sys
from pathlib import Path


NAME_RE = re.compile(r"^[a-z0-9-]+$")
RESERVED_PREFIXES = ("claude-", "anthropic-")

# Markdown frontmatter keys that are documented as scalar strings. A raw value
# that begins with an unquoted ``[`` or ``{`` is a YAML flow collection, which
# either parses as the wrong type or, when two flow sequences sit on one line
# (issue #35), is a hard YAML ParserError that makes loaders drop the skill.
FRONTMATTER_SCALAR_KEYS = (
    "name",
    "description",
    "argument-hint",
    "allowed-tools",
    "user-invocable",
)
FRONTMATTER_STRING_KEYS = ("name", "description", "argument-hint", "allowed-tools")
_FRONTMATTER_KEY_RE = re.compile(r"^([A-Za-z][A-Za-z0-9_-]*):\s*(.*)$")

# Legitimate frontmatter never nests flow collections anywhere near this deep.
# Beyond it the value is unbalanced or hostile: PyYAML's pure-Python loader
# dies with RecursionError (not YAMLError), so the depth is bounded here in
# the dependency-free pass instead of relying on the parser to complain.
FRONTMATTER_MAX_FLOW_DEPTH = 100

# Vendored trees, VCS internals and tool caches. Build output directories are
# intentionally absent: they can contain shipped skills.
EXCLUDED_DIR_PARTS = frozenset((
    "node_modules", ".git", "__pycache__", ".pytest_cache", ".ruff_cache",
    ".venv", "venv",
))

try:
    import yaml as _yaml
except ImportError:
    _yaml = None


def discover_manifests(root):
    """Return every supported manifest location under *root*."""
    paths = [
        root / ".claude-plugin/plugin.json",
        root / ".claude-plugin/marketplace.json",
        root / ".codex-plugin/plugin.json",
        root / ".cursor-plugin/plugin.json",
        root / "openclaw/openclaw.plugin.json",
    ]
    for plugin in (root / "plugins").glob("*") if (root / "plugins").is_dir() else ():
        paths.extend((
            plugin / ".claude-plugin/plugin.json",
            plugin / ".claude-plugin/marketplace.json",
            plugin / ".codex-plugin/plugin.json",
            plugin / ".cursor-plugin/plugin.json",
        ))
    return sorted(path for path in paths if path.is_file())


def _is_excluded(path, root):
    """True when *path* lives under a directory this gate does not validate.

    Test fixtures and scan corpora hold sample skills that are malformed on
    purpose, so they are out of scope; only shipped skills are validated.
    """
    parts = path.relative_to(root).parts
    if EXCLUDED_DIR_PARTS.intersection(parts):
        return True
    for index in range(len(parts) - 1):
        if parts[index] == "tests" and parts[index + 1] in ("fixtures", "corpus"):
            return True
    return False


def discover_skill_markdown(root):
    """Return every ``SKILL.md`` and command markdown file under *root*.

    Command markdown is any ``*.md`` file beneath a ``commands`` directory.
    Files without YAML frontmatter are filtered out by the caller, and test
    fixtures / corpora are skipped (see :func:`_is_excluded`).
    """
    root = Path(root)
    paths = set()
    # An unreadable directory anywhere under root must not abort the gate with a
    # PermissionError traceback.
    try:
        paths.update(root.rglob("SKILL.md"))
        for commands_dir in root.rglob("commands"):
            if commands_dir.is_dir():
                paths.update(commands_dir.rglob("*.md"))
    except OSError:
        pass
    return sorted(
        path for path in paths
        if path.is_file() and not _is_excluded(path, root)
    )


def _extract_frontmatter(text):
    """Return the raw frontmatter block (between the opening and closing ``---``).

    Returns ``None`` when *text* does not start with a frontmatter fence.
    """
    lines = text.lstrip("").splitlines()
    if not lines or lines[0].rstrip() != "---":
        return None
    for index in range(1, len(lines)):
        # The closing fence must sit at column 0, so that an indented ``---``
        # inside a block scalar (such as a ``description: |`` containing a
        # markdown horizontal rule) does not end the block early.
        if lines[index].rstrip() == "---":
            return "\n".join(lines[1:index])
    return None


def _flow_depth(value):
    """Return the deepest flow-collection nesting in *value*.

    Counts ``[``/``{`` openers against ``]``/``}`` closers, ignoring quoting;
    for a sanity bound that approximation is fine.
    """
    depth = deepest = 0
    for char in value:
        if char in "[{":
            depth += 1
            deepest = max(deepest, depth)
        elif char in "]}":
            depth = max(0, depth - 1)
    return deepest


def _structural_frontmatter_check(violations, relative, block):
    """Flag scalar keys whose raw value begins with an unquoted flow collection.

    Works with zero third-party dependencies. Catches issue #35
    (``argument-hint: [a] [b]``) which is a hard YAML ParserError, and also
    catches single flow collections (``argument-hint: [single]``) that parse
    as a list instead of the documented string type. Flow collections nested
    deeper than ``FRONTMATTER_MAX_FLOW_DEPTH`` are flagged on any key, since
    they kill the real parser with RecursionError rather than a YAMLError.
    """
    for line in block.splitlines():
        match = _FRONTMATTER_KEY_RE.match(line)
        if not match:
            continue
        key, value = match.group(1), match.group(2)
        if value and value[0] in "[{" \
                and _flow_depth(value) > FRONTMATTER_MAX_FLOW_DEPTH:
            _failure(
                violations, relative, "frontmatter",
                "flow collection nested deeper than {} levels; unbalanced or "
                "hostile nesting crashes strict YAML loaders".format(
                    FRONTMATTER_MAX_FLOW_DEPTH),
            )
            continue
        if key not in FRONTMATTER_SCALAR_KEYS or not value:
            continue
        if value[0] in "[{":
            _failure(
                violations, relative, key,
                "value begins with unquoted '{}': YAML flow collection on a "
                "documented string key; quote the value".format(value[0]),
            )


def _validate_frontmatter(violations, relative, text):
    """Validate the YAML frontmatter of a single markdown file."""
    block = _extract_frontmatter(text)
    if block is None:
        return
    _structural_frontmatter_check(violations, relative, block)
    if _yaml is None:
        return
    try:
        data = _yaml.safe_load(block)
    except (_yaml.YAMLError, RecursionError) as exc:
        # Deeply nested flow collections raise RecursionError rather than
        # YAMLError, so both are reported as a parse violation.
        _failure(violations, relative, "frontmatter", "YAML parse error: {}".format(
            type(exc).__name__ if isinstance(exc, RecursionError) else exc))
        return
    if not isinstance(data, dict):
        _failure(violations, relative, "frontmatter", "must be a YAML mapping")
        return
    for key in FRONTMATTER_STRING_KEYS:
        if key in data and not isinstance(data[key], str):
            _failure(
                violations, relative, key,
                "must be a string, got {}".format(type(data[key]).__name__),
            )


def _failure(violations, path, field, message):
    violations.append({"file": str(path), "field": field, "message": message})


def _check_name(violations, path, field, value):
    if not isinstance(value, str) or not NAME_RE.fullmatch(value):
        _failure(violations, path, field, "must be kebab-case ([a-z0-9-]+)")
    elif value.startswith(RESERVED_PREFIXES):
        _failure(violations, path, field, "must not start with claude- or anthropic-")


def _check_author(violations, path, field, value):
    if not isinstance(value, dict) or not isinstance(value.get("name"), str):
        _failure(violations, path, field, "must be an object with a string name")


def validate_manifests(root):
    """Return all manifest violations beneath *root* without raising on bad JSON."""
    root = Path(root).resolve()
    canonical_path = root / ".claude-plugin/plugin.json"
    violations = []
    manifests = discover_manifests(root)
    parsed = {}

    for path in manifests:
        relative = path.relative_to(root)
        try:
            with path.open(encoding="utf-8") as handle:
                parsed[path] = json.load(handle)
        except (OSError, json.JSONDecodeError) as exc:
            _failure(violations, relative, "JSON", "invalid JSON: {}".format(exc))

    canonical = parsed.get(canonical_path)
    canonical_version = canonical.get("version") if isinstance(canonical, dict) else None
    if canonical_version is None:
        _failure(violations, canonical_path.relative_to(root), "version", "canonical version is missing")

    for path, data in parsed.items():
        relative = path.relative_to(root)
        if not isinstance(data, dict):
            _failure(violations, relative, "manifest", "must be a JSON object")
            continue
        marketplace = path.name == "marketplace.json"

        if marketplace:
            _check_name(violations, relative, "name", data.get("name"))
            if "owner" in data and not isinstance(data["owner"], dict):
                _failure(violations, relative, "owner", "must be an object")
            metadata = data.get("metadata", {})
            if isinstance(metadata, dict) and "version" in metadata:
                _check_version(violations, relative, "metadata.version", metadata["version"], canonical_version)
            plugins = data.get("plugins", [])
            if not isinstance(plugins, list):
                _failure(violations, relative, "plugins", "must be a list")
                continue
            for index, plugin in enumerate(plugins):
                prefix = "plugins[{}]".format(index)
                if not isinstance(plugin, dict):
                    _failure(violations, relative, prefix, "must be an object")
                    continue
                _check_name(violations, relative, prefix + ".name", plugin.get("name"))
                if "author" in plugin:
                    _check_author(violations, relative, prefix + ".author", plugin["author"])
                if "version" in plugin:
                    _check_version(violations, relative, prefix + ".version", plugin["version"], canonical_version)
        elif path.name == "openclaw.plugin.json":
            # OpenClaw is a separate ecosystem: `id` is the kebab identifier and
            # `name` is a human-readable display string (spaces/caps allowed).
            # Do not impose Claude Code's name rules on it.
            if "id" in data:
                _check_name(violations, relative, "id", data["id"])
            if "author" in data:
                _check_author(violations, relative, "author", data["author"])
            if "version" in data:
                _check_version(violations, relative, "version", data["version"], canonical_version)
        else:
            _check_name(violations, relative, "name", data.get("name"))
            if "author" in data:
                _check_author(violations, relative, "author", data["author"])
            if "version" in data:
                _check_version(violations, relative, "version", data["version"], canonical_version)

    for path in discover_skill_markdown(root):
        relative = path.relative_to(root)
        try:
            text = path.read_text(encoding="utf-8")
        except (OSError, UnicodeDecodeError) as exc:
            # UnicodeDecodeError is a ValueError, not an OSError: a non-UTF-8
            # SKILL.md must be reported as a violation, never crash the gate.
            _failure(violations, relative, "SKILL.md", "could not read: {}".format(exc))
            continue
        _validate_frontmatter(violations, relative, text)

    return manifests, violations


def _check_version(violations, path, field, value, canonical_version):
    if canonical_version is not None and value != canonical_version:
        _failure(
            violations, path, field,
            "version {} does not match canonical version {}".format(value, canonical_version),
        )


def main(argv=None):
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--root", type=Path, default=Path(__file__).resolve().parents[3])
    parser.add_argument("--json", action="store_true", dest="as_json")
    parser.add_argument(
        "--require-yaml", action="store_true",
        help="fail instead of falling back to the weaker structural-only "
             "frontmatter check when PyYAML is unavailable (use in CI)",
    )
    args = parser.parse_args(argv)

    # Without PyYAML the frontmatter check covers only the structural pass.
    # --require-yaml fails closed; otherwise the reduced scope is reported.
    degraded = _yaml is None
    if degraded and args.require_yaml:
        print("ERROR: PyYAML is required for full frontmatter validation "
              "(--require-yaml was passed); install pyyaml", file=sys.stderr)
        return 2
    if degraded:
        print("WARNING: PyYAML not installed - frontmatter checks limited to "
              "the structural pass (no YAML parse or type validation)",
              file=sys.stderr)

    manifests, violations = validate_manifests(args.root)

    if args.as_json:
        print(json.dumps({"valid": not violations, "manifests": len(manifests),
                          "violations": violations, "yaml_available": not degraded}, indent=2))
    elif violations:
        for violation in violations:
            print("ERROR: {file}: {field}: {message}".format(**violation))
    else:
        print("OK: {} manifests valid".format(len(manifests)))
    return 1 if violations else 0


if __name__ == "__main__":
    sys.exit(main())
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall