Skip to content

panjose/Co-Scientist / skills/skills-codex-entry/co-scientist-run

co-scientist-run

Verified

Bootstrap an existing Co-Scientist run directory from Codex.

co-scientist-run

Goal:

  • Bootstrap one existing Co-Scientist run and continue with the canonical pipeline.

Expected input:

  • one run directory such as runs/test1
  • or one compatibility config path such as runs/test1/config.yaml

Execution steps:

  1. Resolve the run directory or config path relative to the repository root.

  2. Run:

    python -m tools.host.project_cli run <run-target> --skill co-scientist-pipeline
    
  3. Read runs/<run_id>/state/HOST_AGENT_HANDOFF.json.

  4. Read the CLI JSON result and the run-local dashboard receipt artifacts:

    • runs/<run_id>/dashboard/LINKS.md
    • runs/<run_id>/dashboard/LINKS.json
  5. If the CLI JSON contains dashboardLinks:

    • If dashboard.status is running, return dashboardLinks.dashboard as the primary dashboard URL and include the deep links.
    • If dashboard.status is starting, immediately run:
    python -m tools.host.project_cli dashboard <run-dir>
    
    • Read the refreshed CLI JSON result plus runs/<run_id>/dashboard/LINKS.md.
    • If runtime.status is now running, return the refreshed links.dashboard URL as the primary dashboard URL and include the deep links.
    • If runtime.status is still starting, tell the user that the dashboard is still booting, point them to runs/<run_id>/dashboard/LINKS.md, and include the retry command:
    $co-scientist-dashboard <run-dir>
    
  6. Open skills/co-scientist-pipeline/SKILL.md and the shared references listed by the handoff.

  7. Continue from the canonical repository-local workflow instead of inventing a parallel flow. If the refreshed routing plan returns run_configuration, execute research-config and validate research_plan/RESEARCH_PLAN.json before any generation work.

  8. After major phase writes, run:

    python -m tools.validation.contract_validation runs/<run_id> --skill co-scientist-pipeline
    

Rules:

  • Use persisted artifacts as the source of truth.
  • Do not skip research-config when routing requires run_configuration.
  • The first active stage may be Configuration rather than Generation; do not skip it when the routing plan requires run_configuration.
  • Treat skills/ as canonical and .agents/skills/ as the installed Codex discovery surface.
  • Treat runs/<run_id>/dashboard/LINKS.md as the human-readable dashboard receipt and runs/<run_id>/dashboard/LINKS.json as the machine-readable receipt.
  • Under completion_driven + auto, continue until the routing plan reaches overview, a configured checkpoint, or a blocking validator/safety state.
  • If you must stop before convergence or a terminal route, tell the user the run is paused, current convergence has not been reached, persisted state is resumable, and the next recommended action is continue evolution through $co-scientist-resume <run-dir> or an explicit continue request.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall