Skip to content
Back to skills

Session Review

ASecurity

Perform a comprehensive white-box review of the session's concrete Axl net diff using independent Codex reviewers; triage findings, fix confirmed defects, verify, and commit. Use only when the user explicitly invokes $session-review.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 18, 2026
ai-agentsapi

Works with

  • api

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 18, 2026

npx -y skills add axl-sdk/axl --skill session-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Session Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Session Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/axl-sdk-session-review-axl/badge)](https://www.skillsdirectory.com/skills/axl-sdk-session-review-axl)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: session-review
description: Perform a comprehensive white-box review of the session's concrete Axl net diff using independent Codex reviewers; triage findings, fix confirmed defects, verify, and commit. Use only when the user explicitly invokes $session-review.
---

# Session Review

Review the session's net diff by following
`.claude/skills/session-review/references/procedure.md` (also linked as
`references/procedure.md` beside this file; read it now). This file binds the
procedure's lanes to Codex.

## Lane bindings

| Lane                 | Agent                                                                                                   |
| -------------------- | ------------------------------------------------------------------------------------------------------- |
| Review, composite    | `reviewer` with the composite charter                                                                   |
| Review, focused seam | `senior-reviewer` with the focused seam charter                                                         |
| Cross-platform pass  | a Claude `senior-reviewer` for consequential seams, run by the owner; this session triages its findings |
| Implementation       | `implementer` for established contracts; `senior-implementer` for consequential seams                   |
| Hard problems        | `senior-implementer` for uncertain diagnosis and consequential fixes                                    |
| Live-API pass        | the lead, via `$live-api-verification` with the checklist path                                         |

## Platform mechanics

- Start reviewers and blind analysts in fresh context (`fork_turns="none"` when the host exposes that option). Supply raw requirements and artifacts, not the implementation conversation or persuasive rationale. A blind analyst receives only requirements and public behavior until its matrices are frozen.
- Reviewers run read-only; agents return reports through the host final-result channel. Resume the same agent thread for a recheck.

Files in this skill

  • SKILL.md2 KB
  • agents/openai.yaml229 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.