codex
Use OpenAI Codex CLI for complex debugging, code analysis, or when stuck on difficult problems.
Skill by shrivatsas
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/shrivatsas-codex
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.
About
Use cases: agent-building
Reviews
Write a reviewNo 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/codex
What's inside
- Skill name
codex- Description
- Use OpenAI Codex CLI for complex debugging, code analysis, or when stuck on difficult problems. Invokes Codex with a file-based question/answer pattern.
- License
- MIT
- Instructions
- 84 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Using Codex for Complex Debugging When you encounter a difficult problem that would benefit from a second perspective or deep analysis, use Codex via the file-based pattern. ## When to Use - Debugging subtle bugs (bitstream alignment, off-by-one errors) - Analyzing complex algorithms against specifications - Getting detailed code review with specific bug identification - Understanding obscure file formats or protocols - When you've tried multiple approaches and are stuck ## The Pattern ### Step 1: Create a Question File Write to `/tmp/question.txt` with: - Clear problem statement - The specific error or symptom - The relevant code (full functions, not snippets) - What you've already tried - Specific questions you want answered - Request: "Please write a detailed analysis to /tmp/reply.txt" Example structure: ``` I have a [component] that fails with [specific error]. Here is the full function: [paste complete code] Key observations: 1. [What works] 2. [What fails] 3. [When it fails] Can you identify: 1. [Specific question 1] 2. [Specific question 2] Please write a detailed analysis to /tmp/reply.txt ``` ### Step 2: Invoke Codex ```bash cat /tmp/question.txt | codex exec --full-auto ``` Flags: - `exec`: Non-interactive execution mode (required for CLI use) - `--full-auto`: Run autonomously without prompts Do NOT use the `-o` flag. The prompt already instructs Codex to write its analysis to `/tmp/reply.txt` via its own shell commands. Using `-o /tmp/reply.txt` would overwrite the actual analysis with Codex's conversational stdout (e.g. "Wrote the analysis..."). ### Step 3: Read the Reply Read `/tmp/reply.txt` and evaluate suggestions critically. Codex may identify real bugs but can occasionally misinterpret specifications. ## Tips 1. **Provide complete code**: Don't truncate functions. Codex needs full context. 2. **Be specific**: "Why does Huffman decoding fail after 1477 blocks?" > "Why does this fail?" 3. **Include the spec**: Mention relevant spec sections if debugging against a standard. 4. **Verify suggestions**: Codex is helpful but not infallible. Always verify against authoritative sources. 5. **Iterate if needed**: Create a new question.txt with additional context if first response doesn't solve the problem. ## Common Issues - **"stdin is not a terminal"**: Use `codex exec` not bare `codex` - **No output**: Check that `-o` flag has a valid path - **Timeout**: Complex questions take time; `--full-auto` avoids blocking prompts ## Quick Alternative For shorter questions: ```bash echo "Explain the JPEG progressive AC refinement algorithm" | codex exec --full-auto ``` But for debugging, the file-based pattern is better for refining questions and keeping records.
From shrivatsas/dev-setup, MIT.
More from shrivatsas/dev-setup
- 0.512score
architecture-docs
shrivatsas
Generate or update architecture documentation from repositories, product docs, infrastructure files, and code.
SkillCFreshness: C★ 2Claude Code +9 - 0.512score
domain-driven-design
shrivatsas
DDD planning and review workflow for greenfield systems and brownfield codebases.
SkillCFreshness: C★ 2Claude Code +9 - 0.503score
sync-dev-skills
shrivatsas
Copy the skills collection from /Users/shrivatsa/Documents/dev-setup/skills into the current repository, another repository, or an explicit skills directory.
SkillCFreshness: C★ 2Claude Code +9 - 0.493score
Condition-Based Waiting
shrivatsas
Replace arbitrary timeouts with condition polling for reliable async tests
SkillCFreshness: C★ 2Claude Code +9 - 0.493score
Gardening Skills Wiki
shrivatsas
Maintain skills wiki health - check links, naming, cross-references, and coverage
SkillCFreshness: C★ 2Claude Code +9 - 0.477score
grill-me
shrivatsas
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 25, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/shrivatsas/dev-setup
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from shrivatsas
- 0.512score
architecture-docs
shrivatsas
Generate or update architecture documentation from repositories, product docs, infrastructure files, and code.
SkillCFreshness: C★ 2Claude Code +9 - 0.512score
domain-driven-design
shrivatsas
DDD planning and review workflow for greenfield systems and brownfield codebases.
SkillCFreshness: C★ 2Claude Code +9 - 0.503score
sync-dev-skills
shrivatsas
Copy the skills collection from /Users/shrivatsa/Documents/dev-setup/skills into the current repository, another repository, or an explicit skills directory.
SkillCFreshness: C★ 2Claude Code +9 - 0.493score
Condition-Based Waiting
shrivatsas
Replace arbitrary timeouts with condition polling for reliable async tests
SkillCFreshness: C★ 2Claude Code +9 - 0.493score
Gardening Skills Wiki
shrivatsas
Maintain skills wiki health - check links, naming, cross-references, and coverage
SkillCFreshness: C★ 2Claude Code +9 - 0.477score
grill-me
shrivatsas
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: C★ 2Claude Code +9
Cite this page
codex skill. Agent Mart. https://agentmart.dev/skills/shrivatsas-codex (last updated 2026-10-24)