Agent skill
codex-read
Read and integrate response from Codex. Use when user says codex read, get codex response, or check codex results.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/codex-read
SKILL.md
Codex Read Skill
Read the response from Codex and integrate findings.
Steps
Before any file operations, resolve the .agent-collab directory so commands work outside the project root:
AGENT_COLLAB_DIR="${AGENT_COLLAB_DIR:-}"
if [ -n "$AGENT_COLLAB_DIR" ]; then
if [ -d "$AGENT_COLLAB_DIR/.agent-collab" ]; then
AGENT_COLLAB_DIR="$AGENT_COLLAB_DIR/.agent-collab"
elif [ ! -d "$AGENT_COLLAB_DIR" ]; then
AGENT_COLLAB_DIR=""
fi
fi
if [ -z "$AGENT_COLLAB_DIR" ]; then
AGENT_COLLAB_DIR="$(pwd)"
while [ "$AGENT_COLLAB_DIR" != "/" ] && [ ! -d "$AGENT_COLLAB_DIR/.agent-collab" ]; do
AGENT_COLLAB_DIR="$(dirname "$AGENT_COLLAB_DIR")"
done
AGENT_COLLAB_DIR="$AGENT_COLLAB_DIR/.agent-collab"
fi
If $AGENT_COLLAB_DIR does not exist, stop and ask for the project root.
1. Check Status
Read $AGENT_COLLAB_DIR/status:
idle: No pending task. Inform user.pending: Codex hasn't started. Check Codex pane.working: Codex still processing. Wait.done: Proceed to read response.
2. Read Response
Read $AGENT_COLLAB_DIR/responses/response.md and parse:
- Task type completed
- Findings/output
- Any code produced
- Recommendations
3. Present to User
Summarize clearly based on task type:
For CODE_REVIEW:
- Bugs/issues with severity
- Security concerns
- Performance issues
- Suggested improvements
For IMPLEMENT:
- What was implemented
- Approach taken
- Integration instructions
For PLAN_REVIEW:
- Critique summary
- Identified risks
- Alternative suggestions
4. Integrate (if applicable)
For implementations:
- Ask if user wants to integrate
- Apply changes if yes
- Run relevant tests
5. Reset Status
Write idle to $AGENT_COLLAB_DIR/status
6. Next Steps
Suggest appropriate follow-up:
- Reviews: Address issues found
- Implementations: Test and validate
- Plan reviews: Iterate on plan
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?