dev-loop

Solid

Research → Execute → Dual-Review Loop (Code Quality + Issue Resolution) bis beide Reviews bestanden

AI & Automation 5 stars 0 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
26
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
65
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

## System Prompt Addition Implement tasks in a structured 3-phase loop: 1. **Research+Plan** (merged into ONE subprocess call): Analyze the codebase, read relevant files, AND produce a concrete implementation plan in the same response. Search the web only when local code and docs are insufficient. Output: `.dev-loop/research-and-plan.md`. 2. **Execute**: Implement the solution based on the research+plan output. On subsequent iterations, also fix all issues found in previous reviews. 3. **Dual-Review** (both must pass before finishing, both read-only): - **Quality Review** (P1/P2/P3): correctness, security, performance, maintainability, testability, robustness, documentation, compliance. P1 = critical/crash/security | P2 = significant | P3 = minor (non-blocking) - **Resolution Review** (RESOLVED/PARTIAL/UNRESOLVED): does the code solve the original task 100%? Quality is irrelevant here — only task completion matters. Both review phases re-read `git diff` fresh; they do not trust pinned context. Loop repeats until both reviews pass. No auto-commit or push. Output written to `.dev-loop/`. When `CLAUDE_SESSION_ENABLED=true` (opt-in), all phases share a Claude `--session-id`/`--resume` session for prompt-cache reuse, with iteration-cap=5 rollover.

Details

Author
swDomass
Repository
swDomass/AI_orchestrator
Created
5 months ago
Last Updated
3 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Listed

review-loop

Dispatches a multi-agent review team over the work in this session, runs an execution-grounded check (lint/test/build), validates findings through a falsifier stage, addresses load-bearing issues, and re-reviews until clean or budget hits. On the terminal verdict, always records a commit-pinned verdict comment on the branch's open PR (if one exists), so the review leaves a trail. Invoked manually as /review-loop or automatically by the Stop hook after real work outside plan mode. Use `--mode claim` to review a non-code analytical conclusion (a research finding or comparison verdict) by sending reviewers back to its primary sources to falsify it.

0 Updated today
BryceEWatson
AI & Automation Listed

loop-review

Independently review one loop iteration's implementation diff against the product contract and report a verdict (APPROVE, REVISE with must-fix items, or — at the gate — ESCALATE to the human). Requirement-first — per-REQ satisfaction is judged before code quality; the gate renders a machine-parsed verdict per REQ. Runs read-only with fresh context; driven by loop.sh, not for ad-hoc use.

0 Updated 2 days ago
Aitne-sh
Code & Development Solid

review-loop

Convergence-paced review-resolve loop over code/PR diffs. Drives a pluggable review source (codex | code-review), verifies each finding against the codebase and the work-flow, auto-applies mechanical fixes and gates judgment fixes with the user, then re-reviews until the source verdict reaches approve. User-invoked via /review-loop.

125 Updated today
jongwony