Skip to content
Agentmart
Submit a tool

enterprise-review

Use when enterprise implementation is complete enough for a structured review that separates spec compliance from code quality and classifies drift explicitly

Skill by anotherben

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/anotherben-enterprise-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when enterprise implementation is complete enough for a structured review that separates spec compliance from code quality and classifies drift explicitly

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/enterprise-review

What's inside

Skill name
enterprise-review
Description
Use when enterprise implementation is complete enough for a structured review that separates spec compliance from code quality and classifies drift explicitly
License
MIT
Instructions
51 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • evals.json · evals/
  • review-separation.md · references/

SKILL.md (first lines)

# Enterprise Review

Review the work in two stages. Never mix them.

## Required Background

- `code-reviewer`
- `requesting-code-review`

## Stage Order

Use [review-separation.md](references/review-separation.md).

1. Stage 1: spec compliance
2. Stage 2: code quality

If Stage 1 fails, Stage 2 does not start.

Before review starts, run the agent-bound review gate in [agent-stage-gates.md](../enterprise/references/agent-stage-gates.md).

For non-trivial, schema-sensitive, tenant-sensitive, money/order/inventory/invoice, or UI workflow changes, review should be multi-agent when available: split spec/contract, schema/data, code execution, E2E/workflow, security/tenant, and headless UI lenses. If delegation is unavailable, run the same lenses sequentially and label the limitation.

## Required Checks

- every contract item has a matching implementation target
- every contract item has a real test
- changed files are classified as `required`, `enabling`, or `drift`
- proof scope in the contract still matches the implementation reality
- contract traceability statuses are updated from `pending` to their real state before handoff
- schema/query claims have current-code reads plus real DB proof, not migrations/diffs/mocks
- every changed runtime file has code-level execution proof
- every cross-layer behavior has source-to-consumer E2E trace and edge-case coverage
- UI/PDF/file/upload/rendered workflows have headless browser proof
- repo gate matrix commands are present and credible: PR body/delivery gate, no-new-mock guard, DB ownership gate, live-proof registry, and required CI mirrors
- the review is against the current final diff. If CI or a gate forced a code pivot, earlier review output for affected files is stale and must be rerun.

## Reviewer Independence

If an independent reviewer is available for medium or large work, use one. If not, perform the review yourself but label the limitation explicitly. Do not pretend self-review is the same as independent review.

If the prompt explicitly states that the committed repo profile and repo-local overlay are already current, review should proceed without reopening discover work unless the diff reveals profile drift.

When the review artifact is written, record it in the current agent session before moving to forge or verify.

## Completion Handoff

- Writing the review artifact is not the finish line.
- If the current prompt asks for completion, verification, or an end-to-end cycle, review must hand off directly to `enterprise-verify` in the same lane.
- Do not stop after review waiting for another prompt unless the user explicitly asked for review-only output.

From anotherben/agentic-governance, MIT.

More from anotherben/agentic-governance

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 4, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from anotherben

Cite this page

enterprise-review skill. Agent Mart. https://agentmart.dev/skills/anotherben-enterprise-review (last updated 2026-10-24)