autoresearch
Stateful validator-gated research loop with native-hook persistence
How do I install this agent skill?
npx skills add https://github.com/yeachan-heo/oh-my-codex --skill autoresearchIs this agent skill safe to install?
- Gen Agent Trust Hubwarn
The skill defines a stateful research loop that relies on dynamic command execution from state files and is vulnerable to indirect prompt injection through processed research data and validator outputs.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Autoresearch
Autoresearch is the skill-first replacement for the deprecated omx autoresearch command.
It keeps the useful measured-research loop, but it now runs as a native-hook stateful workflow instead of a direct CLI or tmux launch surface.
Boundary with planning research
Use $autoresearch when the research output itself is a bounded deliverable that must pass an explicit validator. Do not recommend it for ordinary pre-planning docs lookup or general best-practice checks; use $best-practice-research for that. If $autoresearch is intentionally run before architecture planning, its approved artifact should feed evidence into $ralplan; it should not become a final architecture/component unless the user explicitly asks for ongoing research automation.
Use when
- You want a Ralph-ish persistent research loop
- The task should keep nudging until explicit validation evidence exists
- You want init-time choice between script validation and prompt+architect validation
Do not use when
- You want the old
omx autoresearchcommand surface (hard-deprecated) - You want detached tmux or split-pane launch parity
- You have not decided the validation regime yet
Core contract
- Init chooses validation mode. Pick exactly one:
mission-validator-scriptprompt-architect-artifact
- Persist mode state in
.omx/state/.../autoresearch-state.jsonincluding:validation_modecompletion_artifact_pathmission_validator_commandorvalidator_prompt- optional
output_artifact_path
- Completion is artifact-gated. The loop does not stop because the model says “done”, because a stop hook fired once, or because several turns were no-ops.
- Direct CLI launch is gone. Use
$deep-interview --autoresearchfor intake and$autoresearchfor execution.
Completion artifact contract
mission-validator-script
The completion artifact must exist and record a passing validator result, for example:
{
"status": "passed",
"passed": true,
"summary": "metric improved beyond baseline"
}
prompt-architect-artifact
The completion artifact must include both an architect approval verdict and an output artifact path, for example:
{
"validator_prompt": "Review the research output against the mission.",
"architect_review": { "verdict": "approved" },
"output_artifact_path": ".omx/specs/autoresearch-demo/report.md"
}
Recommended flow
- Run
$deep-interview --autoresearchto clarify mission + evaluator. - Materialize
.omx/specs/autoresearch-{slug}/mission.md,sandbox.md, andresult.json. - Start
$autoresearchwith the chosen validation mode stored in mode state. - Let stop-hook / auto-nudge continue until the completion artifact satisfies the chosen validation mode.
- Finish only after the validator artifact is complete.
Migration note
omx autoresearchis hard-deprecated.- No direct CLI launch.
- No tmux split-pane launch.
- No noop-count completion gate.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/yeachan-heo/oh-my-codex/autoresearch">View autoresearch on skillZs</a>