review-loop SKILL.md skillA

review-loop from spxrogers/agentsync is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add spxrogers/agentsync/review-loop@git:20260801.904b948

Pins git:20260801.904b948 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
spxrogers/agentsync
Path
.agents/skills/review-loop/SKILL.md
Versions recorded
3
Latest version
git:20260801.904b948, committed Aug 1, 2026
First version recorded
Jun 5, 2026
Size
25,422 bytes
Repository stars
40
License
MIT

'Multi-round adversarial code review loop — four specialized agents (correctness,.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Review loop

A four-lens adversarial review pattern, iterated until the team converges or a
budgeted number of rounds elapses. Use it when the user wants the bar set
high on both **correctness** and **polish** — substantive PRs where a single
review pass would miss the second-order issues four lenses catch
independently.

Loop logic:

```
for round in 1..N:                          # N defaults to 5
  launch 4 READ-ONLY agents IN PARALLEL: correctness, adversarial, api-design, test-rigor
  wait for all 4 to report                  # they report; they never edit
  synthesize findings (convergent vs single-reviewer; rank by severity)
  if every reviewer says "CLEAN — ship it":
    stop                                    # full convergence
  if every finding this round is NIT severity (no BLOCKER/ISSUE anywhere):
    ask the user: stop here, or spend one more round?   # see Step 5
  if severity has trended down for 2 rounds straight and neither stop
     condition above has fired: ask the user ONCE — stop, or continue to budget?
  audit each finding yourself               # reviewers are wrong sometimes
  fix every accepted finding                # MAIN SESSION ONLY — see below
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add spxrogers/agentsync/review-loop@sha256:6fe35b10ad168966

The line at the top of this page pins the label git:20260801.904b948, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_clhi3qmqfk2amhhb.svg)](https://markdownregistry.com/a/art_clhi3qmqfk2amhhb)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Jun 5, 2026 and Aug 1, 2026, about one every 28 days.

versioncommittedcommitsizeaudit
git:20260801.904b948 latest2026-08-01 904b948 25,422 BA view · diff
git:20260730.e837d972026-07-30 e837d97 21,745 BA view · diff
git:20260605.d3c4f1b2026-06-05 d3c4f1b 13,851 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (25422 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

spxrogers/agentsync · 40 stars · license MIT · pushed 2026-10-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_clhi3qmqfk2amhhb
GET https://markdownregistry.com/api/v1/resolve?ref=spxrogers/agentsync/review-loop
GET https://markdownregistry.com/api/v1/blob/6fe35b10ad16896614099498fe910f8c4c4895adf232420309bcf6faf96cc628

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from spxrogers/agentsync

AGENTS.md@.agentsync/memory AGENTS.md file
spxrogers/agentsync · .agentsync/memory/AGENTS.md
git:20260919.68d897a · audit A · 40 stars
review-loop SKILL.md skill
spxrogers/agentsync · .agentsync/skills/review-loop/SKILL.md · 'Multi-round adversarial code review loop — four specialized agents (correctness,
git:20260801.904b948 · audit A · 40 stars
review-loop SKILL.md skill
spxrogers/agentsync · .claude/skills/review-loop/SKILL.md · 'Multi-round adversarial code review loop — four specialized agents (correctness,
git:20260801.904b948 · audit A · 40 stars
AGENTS.md AGENTS.md file
spxrogers/agentsync · AGENTS.md
git:20260919.68d897a · audit A · 40 stars
CLAUDE.md CLAUDE.md file
spxrogers/agentsync · CLAUDE.md
git:20260919.68d897a · audit A · 40 stars
llms.txt@website/public llms.txt file
spxrogers/agentsync · website/public/llms.txt
git:20260728.c6ad04e · audit A · 40 stars

Every file in spxrogers/agentsync

Other files named review-loop

review-loop SKILL.md skill
aiskillstore/marketplace · skills/2dmurali/review-loop/SKILL.md · Iterative worker-reviewer cycle that spawns a critic subagent to score work 1-10 and provide actionable feedback, then…
git:20260807.8870cf5 · audit A · 471 stars
review-loop SKILL.md skill
parcha-ai/parcha-skills · review-loop/skills/review-loop/SKILL.md · Drive every reviewer thread on a GitHub pull request to zero unresolved, iterating until the exit criterion is met…
git:20261003.22b7ecf · audit A · 123 stars
review-loop SKILL.md skill
timharris707/skills · skills/in-progress/review-loop/SKILL.md · Have a second model review a branch on this machine before its pull request opens, fix what holds up, and repeat until…
git:20261029.b6a29f5 · audit A · 44 stars
review-loop SKILL.md skill
spxrogers/agentsync · .claude/skills/review-loop/SKILL.md · 'Multi-round adversarial code review loop — four specialized agents (correctness,
git:20260801.904b948 · audit A · 40 stars
review-loop SKILL.md skill
spxrogers/agentsync · .agentsync/skills/review-loop/SKILL.md · 'Multi-round adversarial code review loop — four specialized agents (correctness,
git:20260801.904b948 · audit A · 40 stars
review-loop SKILL.md skill
stone16/harness-engineering-skills · plugins/harness-engineering-skills/skills/review-loop/SKILL.md · Run a bounded cross-model peer review and fix loop, or report findings in read-only mode.
v1.4.0 · audit A · 31 stars
review-loop SKILL.md skill
jongwony/cc-plugin · review-loop/skills/review-loop/SKILL.md · Convergence-paced review-resolve loop over a change and its governing surfaces. Verifies each finding against the…
git:20261102.cc3d01b · audit A · 11 stars
review-loop SKILL.md skill
nytc69/review-loop · skills/review-loop/SKILL.md · Drive a work item through the paired-session coordinator (plan → review → implement → CR, then polish, docs and…
git:20261026.5da9fa5 · audit A · 3 stars

Browse by kind, by grade A, or by owner.