Home / nytc69 / review-loop · skills/execute/SKILL.md · GitHub

execute skillA

execute is agent-read markdown (skill) from nytc69/review-loop: Run the execution + quality polish + delivery stages of review-loop against one of three entry modes: resume an approved session (`--session`), execute a user-supplied plan (`--plan`), or run a pure-CR pass on the current working tree (`--review-only`). Supports batched runs via `--stop-after STAGE`. Use when you already have a plan, or only want CR on existing code..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# execute — claude orchestration

Read `docs/protocol/loading.md`, then run:

```bash
python3 <support-root>/scripts/read_protocol.py --runtime claude --stage entry-execute
```

Resolve <support-root> to this plugin/repository, not the task workspace.
Keep cwd in the user's workspace. Read the complete emitted text before acting.
`docs/protocol/loading.json` is the action/prerequisite map for both runtimes.

Validate the three mutually-exclusive entry modes before locking. Run session-init for a fresh plan/review-only target, or resume for an existing session; then execution → execution-review → gate → polish → docs → security → delivery. Honor every --stop-after boundary.

Before initialization load `session-init` AND `execute-init`; before a resume
load `resume` AND `execute-init`. Before any work-agent dispatch load the
matching `planning` or `execution` bundle; before review load
`planning-review` or `execution-review`. On planning approval, only the plan-only entry loads `plan-exit`.
The umbrella retains its session/lock and continues directly into execution.
Before a stage transition, retry,
stop or error exit, load its applicable bundle per `loading.md`.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add nytc69/review-loop/execute@git:20260916.8dd269c
Exact content
mdr add nytc69/review-loop/execute@sha256:f75091fc0aed180a

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_r2cinlszcplev4mo.svg)](https://markdownregistry.com/a/art_r2cinlszcplev4mo)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260916.8dd269c latest2026-09-16 8dd269c 3,020 BA view · diff
git:20260916.cadb06c2026-09-16 cadb06c 28,693 BA view · diff
git:20260514.783f1892026-05-14 783f189 23,123 BA view · diff
git:20260510.9a5f4132026-05-10 9a5f413 20,340 BA view · diff
git:20260509.618abfa2026-05-09 618abfa 19,581 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (3020 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

nytc69/review-loop · 3 stars · license Apache-2.0 · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_r2cinlszcplev4mo
GET https://markdownregistry.com/api/v1/resolve?ref=nytc69/review-loop/execute
GET https://markdownregistry.com/api/v1/blob/f75091fc0aed180ac78c74a91c0eb82003c50c6d080e0dc2216e57dfda64e165

Your agent 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.

More from nytc69/review-loop

execute skill
nytc69/review-loop · .agents/skills/execute/SKILL.md · Codex Stage 1 execute skill. Run the execution + quality polish + delivery stages of review-loop against one of three…
git:20260919.2175063 · audit A · 3 stars
guide skill
nytc69/review-loop · .agents/skills/guide/SKILL.md · Codex Stage 1 guide for review-loop and the shared Claude/Codex state model.
git:20260916.8dd269c · audit A · 3 stars
plan skill
nytc69/review-loop · .agents/skills/plan/SKILL.md · Codex Stage 1 planning-only skill. Drives a work item from raw description to a reviewer-approved plan in…
git:20260919.2175063 · audit A · 3 stars
review-loop skill
nytc69/review-loop · .agents/skills/review-loop/SKILL.md · Codex-native Stage 1 review-loop skill. Orchestrates planning and execution with a Codex Executor and Claude/Codex…
git:20260919.2175063 · audit A · 3 stars
CLAUDE.md claude
nytc69/review-loop · CLAUDE.md
git:20260919.2175063 · audit A · 3 stars
DESIGN.md design
nytc69/review-loop · DESIGN.md
git:20260419.3b9deb7 · audit A · 3 stars
code-quality-loop skill
nytc69/review-loop · skills/code-quality-loop/SKILL.md · Iterative review-fix loop: reviews code, auto-fixes issues, repeats until clean or stuck. Finishes with reorganize (for…
git:20260919.2cc1340 · audit A · 3 stars
guide skill
nytc69/review-loop · skills/guide/SKILL.md · Show review-loop usage guide: how it works, commands, configuration, and key features. Use when the user asks for help…
git:20260916.8dd269c · audit A · 3 stars
plan skill
nytc69/review-loop · skills/plan/SKILL.md · Run the planning phase only: drive a work item from raw description to a reviewer-approved plan in…
git:20260916.8dd269c · audit A · 3 stars
reorganize skill
nytc69/review-loop · skills/reorganize/SKILL.md · Reorganize code file structure: rearrange modules, extract reuse, remove redundancy, add section comments. Preserves…
git:20260402.b86bf98 · audit A · 3 stars
review-loop skill
nytc69/review-loop · skills/review-loop/SKILL.md · Automates a Plan-Execute-Review workflow with built-in iteration loops. An Orchestrator coordinates an Executor…
git:20260916.8dd269c · audit A · 3 stars
review-pr skill
nytc69/review-loop · skills/review-pr/SKILL.md · Comprehensive code review using specialized agents. Each agent focuses on a different quality aspect (code, errors…
git:20260919.2cc1340 · audit A · 3 stars

Every file in nytc69/review-loop

Other files named execute

execute skill
yeachan-heo/oh-my-claudecode · skills/execute/SKILL.md · Carry an approved task through to working, verified code
git:20260824.ec2704f · audit A · 39,312 stars
execute skill
alirezarezvani/claude-skills · .gemini/skills/execute/SKILL.md
git:20260821.7405298 · audit C · 26,410 stars
execute skill
zaxbyhub/opencode-swarm · .opencode/skills/execute/SKILL.md · Full execution protocol for MODE: EXECUTE -- task execution, coder retry handling, QA gates, completion evidence, and…
git:20260912.8b7d5a7 · audit A · 478 stars
execute skill
zaxbyhub/opencode-swarm · .claude/skills/execute/SKILL.md · Claude Code adapter for MODE: EXECUTE. Delegates to the canonical opencode-swarm execution protocol.
git:20260711.5972d3e · audit A · 478 stars
execute skill
serbanghita/plan-critique-skills · skills/execute/SKILL.md · Execute the user's plan that has been iteratively refined
git:20260907.caab477 · audit B · 13 stars
execute skill
jkaloger/lazyspec · skills/execute/SKILL.md · Use when carrying out the work a delivery document describes -- building against its task breakdown and acceptance…
git:20260907.31db009 · audit A · 10 stars
execute skill
naimkatiman/continuous-improvement · third-party/oh-my-claudecode/skills/execute/SKILL.md · Carry an approved task through to working, verified code
git:20260906.bface5c · audit A · 7 stars
execute skill
greglas75/zuvo · skills/execute/SKILL.md · Activated when an implementation plan exists. Executes plan tasks in dependency order (independent, non-same-file tasks…
git:20260906.015072f · audit A · 7 stars

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