Home/Skills/Select Review Method by Risk

Select Review Method by Risk

Perform a read-only review of PR, commits, branches, or workspace differences, trace callers, verify requirements, and provide evidence-based findings. The default is an in-depth Solo review.

Tink1.0.0Oct 23, 2026MIT
Get the skill

Requirements

Intended for Codex-class agents that have repository and file access. The files do not provide browser, test tooling, credentials, project data, or permission to modify external systems; other hosts may require adaptation.

  • Clear baseline, target, and current differences
  • Repository rules, available requirements, tests, and relevant failure evidence
  • Host support for subagents is needed only when selecting independent multi-agent coverage

Quick start

  1. After download, first check the in-package documentation, then extract the ZIP to a temporary directory.
  2. When installing the combined set, copy the six Skill folders and the sibling shared folder into the project's .agents/skills/ or personal ~/.agents/skills/. Keep the relative directory structure, and do not treat the outer combined-set directory as one Skill.
  3. When installing an individual ZIP, put its identically named folder into the selected Skills directory and keep its internal shared resources. Back up the same-named Skill before overwriting to avoid duplicate installation.
  4. In Codex, use the exact $code-review-multiagent invocation; if not found, restart the host. When a task requires workflow handoff, install the corresponding companion Skill separately.

Applicable Scenarios

  • Review changes pending merge against requirements and direct callers.
  • Complex changes involving security, data, interface contracts, or tests with independently investigable surfaces.

Usage Steps

  1. Call $code-review-multiagent to clarify the baseline, target, and requirement source.
  2. Trace the direct callers of the modified public symbols, check applicable risks, and also check behaviors required by requirements but completely missing from the diff.
  3. Default to Solo; only assign 2–4 independent review perspectives when complexity truly warrants and host support is available.
  4. Verify and merge findings with the same root cause, and report severity, trigger conditions, location, impact, evidence, and minimal fix direction.

Deliverables

  • Prioritized P0–P3 findings, or a scoped "no provable defect found" conclusion
  • Provide normative, requirement, and runtime acceptance status and validation gaps separately.

Limitations

  • Does not automatically fix, and does not list pure style preferences as defects.
  • Cannot claim that the candidate implementation was reviewed when there is no diff.
  • Static review and passing tests cannot prove browser usability or deployment; missing runtime evidence must be explicitly preserved.

Example Prompts, Not an Actual Execution

Use $code-review-multiagent to review the current workspace differences against the main branch and approved access control requirements. Keep it read-only, trace direct callers and side effects of rejected requests; distinguish confirmed issues from missing runtime evidence.

This guide describes the in-package workflow and does not represent verified cross-model reliability, nor is it an actual acceptance run report.

Inside the skill
SKILL.md
---
name: code-review-multiagent
license: MIT
description: >-
  Review PRs, commits, branches, or workspace changes; trace triggering paths, callers, missing requirements, and cross-layer contracts to produce evidence-backed, graded, deduplicated findings.
  Default to a deep Solo review; use 2–4 subagents only for complex, independent review surfaces. Read-only: no automatic fixes or purely stylistic criticism.
---

# Deep Code Review

Depth comes from tracing behavior and relationships, not checklist length or agent count. Select checks according to actual risk. Reduce repeated reading, recordkeeping, and reporting without omitting applicable risks or treating missing evidence as success.

This skill is read-only, with the report in the conversation. The caller handles any required archival record. Post-fix review does not replace root-cause investigation: identify concrete causal gaps in speculative or symptom-only patches and return them to `bug-fixing`.

## 1. Fix the Scope and Evidence
Included files · 9
code-review-multiagent/LICENSE
code-review-multiagent/MANIFEST.json
code-review-multiagent/README.md
code-review-multiagent/SKILL.md
code-review-multiagent/agents/face-reviewer.md
code-review-multiagent/agents/finding-challenger.md
code-review-multiagent/agents/openai.yaml
code-review-multiagent/shared/invariants.md
…