codex-review
Run OpenAI Codex CLI as an independent reviewer over the current branch, a specific commit, or uncommitted changes. Builds a focused instruction file from the real diff and returns a compact review summary.
What this skill does
<EXTREMELY-IMPORTANT> This skill orchestrates an external reviewer and must stay disciplined. Non-negotiable rules: 1. Read the real diff before writing Codex instructions. 2. Make the instructions specific to the changed areas and likely risks. 3. Never pass secrets or credential values into review instructions. 4. Carry forward exclusion lists on later rounds. 5. Verify returned findings before acting on them. </EXTREMELY-IMPORTANT> # Codex Review ## Inputs - `$request`: Optional scope hint such as `last commit`, `uncommitted`, `auth focus`, or `round 2` ## Goal Use `codex review` to get an external review pass that: - reads the right diff scope - focuses on the actual risk areas in the change set - returns structured findings instead of generic commentary ## Step 0: Verify Codex availability Check: - `which codex` - whatever minimal auth or environment check is needed for the current setup If the CLI is unavailable or not authenticated, explain the blocker and stop. **Success criteria**: Codex can be invoked successfully from the current repository. ## Step 1: Resolve review scope Determine whether to review: - the full branch against its base - uncommitted changes - a specific commit Read the real diff summary and changed-file list before building instructions. If there is no diff, stop and say so explicitly. **Success criteria**: The exact review target is explicit and backed by a real diff. ## Step 2: Write focused review instructions Build a small temporary instruction file that includes: - what changed - the most relevant risk areas - any previously fixed issues to exclude on later rounds - an instruction to verify findings against the actual code - a compact expected output format Keep the instructions concrete. Generic prompts produce weak reviews. **Success criteria**: The instruction file is specific to the actual change set. ## Step 3: Run `codex review` Use the right invocation shape for the selected scope: - `--base <branch>` for branch review - `--uncommitted` for working-tree review - `--commit <sha>` for a single commit Key flags: - `sandbox_permissions` -- codex needs disk read access to verify findings: `-c 'sandbox_permissions=["disk-full-read-access","disk-full-write-access","network-full-access"]'` - `instructions` -- point to the focused instruction file from Step 2: `-c 'instructions="/tmp/codex-review-instructions.md"'` - `--title "<description>"` -- descriptive review title Always capture stderr with `2>&1` (codex logs to stderr). If the review is expected to be long-running, background execution is acceptable. **Success criteria**: Codex runs against the intended scope and returns parseable output. ## Step 4: Summarize findings Report: - review scope - findings by priority - file and line references when available - explicit clean result when no material findings are returned If the user wants fixes, verify each finding locally before changing code. **Success criteria**: The user gets a clear, scoped review summary instead of raw CLI output. ## Step 5: Iterate only with exclusions On later rounds: - add fixed findings to the exclusion section - narrow the scope to new changes where possible - avoid paying for repeated generic full-branch reviews **Success criteria**: Follow-up rounds look for new issues rather than re-reporting old ones. ## Guardrails - Do not run this skill proactively; it is explicit-user-only. - Do not put secrets, tokens, or private config values in the instruction file. - Do not trust findings blindly without local verification. - Do not use Codex review as a substitute for reading the diff first. ## Output Contract Report: 1. the review scope 2. the main focus areas given to Codex 3. findings by priority with locations when available 4. explicit clean result if nothing material was found 5. whether a next round should exclude previously fixed issues
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.