Adonis0123/adonis-skills / skills/open-code-review-loop
open-code-review-loop
UnverifiedRun a bounded OCR-delegation review-fix-re-review loop on a Git workspace until current evidence validates NO_FINDINGS. Use only when the user wants verified findings fixed and independently re-reviewed until clean with codex, claude-code, grok-build, or cursor-cli. Do not use for one-shot open-code-review-delegate or read-only review. A full loop request asks at most once for an unnamed Reviewer (recommending a product other than the host), then runs host mutation checks without further confirmation. Fail closed on missing ocr, reviewer mutation, skipped files, malformed output, stale evidence, or exhausted rounds.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 19.3 KB |
| evals/evals.json | config | 20.8 KB |
| evals/trigger-eval.json | config | 2.5 KB |
| references/adapter-contracts.md | markdown | 13.5 KB |
| references/fix-contract.md | markdown | 2.7 KB |
| references/fix-schema.json | config | 857 B |
| references/review-contract.md | markdown | 3.1 KB |
| references/review-schema.json | config | 2.8 KB |
| scripts/build_review_bundle.pyexecutable | script | 27.0 KB |
| scripts/extract_product_output.py | script | 3.6 KB |
| scripts/test_extract_product_output.py | script | 6.2 KB |
| scripts/test_validate_fix_result.py | script | 5.1 KB |
| scripts/test_validate_round.py | script | 103.0 KB |
| scripts/validate_fix_result.py | script | 5.4 KB |
| scripts/validate_round.pyexecutable | script | 41.4 KB |
scripts/extract_product_output.py
View on GitHub#!/usr/bin/env python3
"""Extract one reviewer/fixer JSON object from a supported CLI envelope."""
from __future__ import annotations
import argparse
from copy import deepcopy
import json
from pathlib import Path
import sys
from typing import Any
PRODUCTS = ("codex", "claude-code", "grok-build", "cursor-cli")
def load_object(path: str) -> dict[str, Any]:
value = json.loads(Path(path).expanduser().read_text(encoding="utf-8"))
if not isinstance(value, dict):
raise ValueError(f"{path} must contain one JSON object")
return value
def require_object(value: Any, field: str) -> dict[str, Any]:
if not isinstance(value, dict):
raise ValueError(f"{field} must contain one JSON object")
return value
def extract(product: str, envelope: dict[str, Any]) -> dict[str, Any]:
if product == "codex":
return envelope
if product == "claude-code":
return require_object(envelope.get("structured_output"), "structured_output")
if product == "grok-build":
return require_object(envelope.get("structuredOutput"), "structuredOutput")
if product == "cursor-cli":
raw = envelope.get("result")
if not isinstance(raw, str):
raise ValueError("result must be a JSON string containing exactly one JSON object")
try:
parsed = json.loads(raw)
except json.JSONDecodeError as error:
raise ValueError(
"result must be a JSON string containing exactly one JSON object"
) from error
return require_object(parsed, "result")
raise ValueError(f"unsupported product: {product}")
def normalize_reviewer_identity(
product: str,
envelope: dict[str, Any],
result: dict[str, Any],
explicit_session_id: str | None,
) -> dict[str, Any]:
if "reviewer" not in result:
return result
reviewer = result.get("reviewer")
if not isinstance(reviewer, dict):
raise ValueError("reviewer must contain one JSON object")
envelope_field = {
"claude-code": "session_id",
"grok-build": "sessionId",
"cursor-cli": "session_id",
}.get(product)
envelope_session_id = envelope.get(envelope_field) if envelope_field else None
trusted_session_id = explicit_session_id or (
envelope_session_id
if isinstance(envelope_session_id, str) and envelope_session_id.strip()
else None
)
normalized = deepcopy(result)
normalized["reviewer"]["product"] = product
normalized["reviewer"]["session_id"] = trusted_session_id
return normalized
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--product", required=True, choices=PRODUCTS)
parser.add_argument("--input", required=True)
parser.add_argument("--output", required=True)
parser.add_argument("--session-id")
return parser.parse_args()
def main() -> int:
args = parse_args()
try:
envelope = load_object(args.input)
result = normalize_reviewer_identity(
args.product,
envelope,
extract(args.product, envelope),
args.session_id,
)
rendered = json.dumps(result, ensure_ascii=False, indent=2) + "\n"
output = Path(args.output).expanduser().resolve()
output.parent.mkdir(parents=True, exist_ok=True)
output.write_text(rendered, encoding="utf-8")
except (OSError, ValueError, json.JSONDecodeError) as error:
print(str(error), file=sys.stderr)
return 2
print(rendered, end="")
return 0
if __name__ == "__main__":
raise SystemExit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |