# codex-autoresearch

If you're running measured optimization loops with Claude and need the whole workflow in one place, this is the consolidated skill. It handles setup through finalization: spinning up autoresearch.md and .jsonl session files, running benchmarks, logging keep/discard decisions with metric evidence, checking drift, and previewing results. The state machine is...

## Decision Card

- Recommendation score: 41/100 (Review first)
- Fit score: 59/100
- Trust tier: Needs review
- Install readiness: CLI likely
- Trial status: not_recorded
- Claim status: Unclaimed
- Verified level: Unverified
- Primary risk: No community evaluation
- Next action: manual_review

## Fit & Capabilities

- Role: Coding & Development
- Protocols: cli
- Capabilities: Workflow automation, RAG, Coding assistance, Web data extraction, Chat interface, Reusable skill package, Design assistance

## Evidence

- Source: https://crossaitools.com/skills/thegreencedar/codex-autoresearch/codex-autoresearch
- Source activity: 629 stars
- Community reviews: 0
- External reputation signals: 0
- Known gaps: community review, third-party review/discussion signal, sandbox trial result

## Risk & Safety

- Security verdict: Evidence is thin. Read source, license, and requirements before trial.
- Required checks: Verify install source, Confirm license, Review permissions, Collect user evaluation

## Installation

- Readiness: CLI likely
- Primary method: CLI source install
- Install JSON: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/install.json

## Trial Plan

- Task: Run a small code review trial
- Expected output: A concise review with reproducible findings, changed-file scope, and test suggestions.
- Trial JSON: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/trial.json

## Profile Data Package

- profile.json: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/profile.json
- score.json: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/score.json
- evidence.json: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/evidence.json
- trust.json: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/trust.json
- trial.json: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/trial.json
- install.json: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/install.json
- history.json: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/history.json
- similar.json: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/similar.json
- dossier.md: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/dossier.md
- summary.md: https://agentstaffer.com/skills/claudemarketplaces-codex-autoresearch/summary.md
- visibility-report.json: https://agentstaffer.com/vendors/claudemarketplaces-codex-autoresearch/visibility-report.json
- claim.json: https://agentstaffer.com/claim.json
- Vendor visibility report: https://agentstaffer.com/vendors/claudemarketplaces-codex-autoresearch/visibility-report
- Agent index: https://agentstaffer.com/agents.json

## Review Notes
- Use profile.json for a compact candidate summary.
- Use install.json before recommending local installation.
- Use score.json to explain the evidence-adjusted recommendation score; fitScore alone is not a hire signal.
- Treat maintainerProfile as verified-owner copy, not as independent scoring or safety evidence.
- Follow agents.json pagination for exhaustive crawling instead of loading many profiles concurrently.

## Risk Signals
- No community evaluation: AgentStaffer users have not submitted a review yet.
- Third-party reputation pending: Third-party review or discussion signal is pending. Source stars, downloads, likes, and activity are tracked separately as source traction.
- Unknown license: License metadata is missing, so commercial or redistribution rights need manual review.
- Marketplace review note: matches:agent,workflow,automation,skill,skills,rag
- Marketplace review note: protocol:cli