Review code changes for correctness defects, regressions, security risks, unsafe behavior, and missing tests. Use when the user asks for a code review, PR review, independent post-change review, or explicitly asks for a dedicated code-reviewer subagent.
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
# Code Reviewer
Delegate review to one independent native subagent when available. Do not use
`codex-subagent` or a nested `codex exec` process.
## Workflow
1. Read repository rules and determine the exact review scope from the working
tree, commit, branch, PR, or files named by the user.
2. Read `references/role.md` completely.
3. Spawn a native subagent with a self-contained read-only review task. Include
the target root, change scope, relevant constraints, and test evidence, but
do not leak a preferred conclusion. Mark it as the dedicated reviewer child
and tell it not to delegate again.
4. Let the reviewer inherit the current model and policy. Require findings to
cite exact files and lines.
5. Check each returned finding against the current source, remove unsupported
claims, present valid findings first, and close the child.
## Native Child Execution
If the current session was explicitly spawned as the dedicated native child for
this role, execute `references/role.md` directly, do not spawn a descendant,
and report `executed_as_native_child`.
## Fallback
If the current session is not already the dedicated child and native subagents
…
The line at the top of this page pins the label git:20261020.62a8ddd, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_hjvwv5wd6nmw2nxq
GET https://markdownregistry.com/api/v1/resolve?ref=alamoooooooo/alamo_hub/code-reviewer
GET https://markdownregistry.com/api/v1/blob/25aec20dd57a2c87fe70a32a772233e867c60e3f02b748543145051500ed086b
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.
alamoooooooo/alamo_hub · packages/engineering_subagent_workflow_kernel/code-architect/SKILL.md · Produce an evidence-grounded implementation architecture for an existing codebase. Use when the user asks for an…
alamoooooooo/alamo_hub · packages/engineering_subagent_workflow_kernel/code-explorer/SKILL.md · Trace existing code paths and explain repository behavior with precise source evidence. Use when the user asks how code…
alamoooooooo/alamo_hub · packages/engineering_subagent_workflow_kernel/code-simplifier/SKILL.md · Simplify recently changed or explicitly scoped code while preserving observable behavior. Use when the user asks to…
alamoooooooo/alamo_hub · packages/engineering_subagent_workflow_kernel/pr-test-analyzer/SKILL.md · Analyze whether tests cover the behavior changed by a commit, branch, PR, patch, or working tree. Use when the user…
alamoooooooo/alamo_hub · packages/github_sync_workflow_kernel/github-sync-agent/SKILL.md · Coordinate an end-to-end GitHub synchronization workflow over a target repository by discovering the real repo root…
alamoooooooo/alamo_hub · packages/memory_hotspot_repair_kernel/memory-fix/SKILL.md · Apply safe, targeted fixes for memory bottlenecks based on a memory review report or direct code inspection. Use when a…
alamoooooooo/alamo_hub · packages/memory_hotspot_repair_kernel/memory-optimizer-agent/SKILL.md · Orchestrate a bounded memory-optimization loop over a codebase by chaining memory-check, memory-fix, smoke validation…
alamoooooooo/alamo_hub · packages/memory_hotspot_repair_kernel/memory-review/SKILL.md · Review code changes after a memory-oriented fix using Codex-style general code review as the baseline, then add…
