Skip to content

ethanplusai/codex-on-crack / plugins/codex-on-crack/skills/crack

Lead substantial Codex builds with one configured implementation worker and lead acceptance. Use when the user requests codex-on-crack, names a model to delegate work to, asks to run subagents through Claude, or requests a lead/worker split. Keep host-only work direct; honor explicit external model choices. Workers must not invoke this orchestrator.

FileKindSize
SKILL.mdskill md8.0 KB
agents/openai.yamlconfig300 B
references/build-records.mdmarkdown2.7 KB
references/checkpoint.mdmarkdown1.3 KB
references/external-lead.mdmarkdown13.9 KB
references/measurement.mdmarkdown1.8 KB
references/model-selection.mdmarkdown2.2 KB
references/parallel.mdmarkdown1.7 KB
references/policy.mdmarkdown494 B
references/replay.mdmarkdown3.2 KB
references/verification.mdmarkdown2.1 KB
references/worker-contract.mdmarkdown1.3 KB
scripts/doctor.mjsscript608 B
scripts/lead.mjsscript26.0 KB
scripts/lib/catalog.mjsscript5.6 KB
scripts/lib/changes.mjsscript13.3 KB
scripts/lib/config.mjsscript6.5 KB
scripts/lib/external-lead.mjsscript56.7 KB
scripts/lib/io.mjsscript3.8 KB
scripts/lib/lead-protocol.mjsscript25.9 KB
scripts/lib/plan.mjsscript9.2 KB
scripts/lib/readiness.mjsscript6.0 KB
scripts/lib/report.mjsscript10.7 KB
scripts/lib/roles.mjsscript8.9 KB
scripts/lib/routing.mjsscript2.7 KB
scripts/lib/toml.mjsscript785 B
scripts/lib/trial.mjsscript12.4 KB
scripts/report.mjsscript2.7 KB
scripts/select.mjsscript3.9 KB
scripts/setup.mjsscript7.0 KB
scripts/trial.mjsscript1.8 KB
scripts/validate-plan.mjsscript2.6 KB
scripts/worktree.mjsscript7.8 KB
templates/checkpoint.mdmarkdown903 B
templates/plan.jsonconfig680 B
templates/spec.mdmarkdown742 B
templates/task-brief.mdmarkdown2.5 KB
templates/task-report.mdmarkdown1.5 KB
viewer/README.mdmarkdown5.9 KB
viewer/bridge.mjsscript16.6 KB
viewer/fixtures/sample.jsonconfig8.2 KB
viewer/package.jsonmanifest187 B
viewer/public/app.mjsscript8.8 KB
viewer/public/index.htmlother1.8 KB
viewer/public/style.cssother4.4 KB
viewer/serve.mjsscript11.2 KB
viewer/src/adapter.mjsscript9.9 KB
viewer/src/emit.mjsscript992 B
viewer/src/model.mjsscript8.9 KB
viewer/src/server.mjsscript4.1 KB
viewer/src/tail.mjsscript1.9 KB
viewer/test/browser.mjsscript2.6 KB
viewer/test/server.test.mjsscript3.2 KB
viewer/test/usage.test.mjsscript9.0 KB
viewer/test/viewer.test.mjsscript5.1 KB

references/parallel.md

View on GitHub
# Optional parallel execution

Use only for independent tasks with explicit ownership and acceptance criteria.
For a dependency plan, validate it with `node scripts/validate-plan.mjs <plan.json>
--repo-root <repo>`. The default cap is one writer; increase it only when the
plan establishes independent work. Skip accepted tasks on resume. Do not rerun
completed waves just because the validator lists their structural order.

Each parallel writer needs an isolated worktree. `node scripts/worktree.mjs add
--repo <repo> --task <id>` requires a clean committed baseline. When user work,
new briefs, or accepted dependency changes are uncommitted, continue sequentially
in the current workspace. Do not auto-commit, discard changes, or ask a worker
to recreate missing prerequisites to evade the guard. A later parallel wave
also requires a valid baseline containing its prerequisites.

Give each child the full brief and actual dependency outputs. Readers may run
alongside writers only when their findings do not require a stable view of the
files those writers are editing. Shared test services and build outputs can
conflict even with disjoint source paths.

After root acceptance, preview integration:
`node scripts/worktree.mjs integrate --repo <repo> --task <id> --allowed <path>`.
Add `--apply` to apply the patch without a commit. Scope violations require a
correction; never enlarge the scope just to make integration pass.

Removal uses `node scripts/worktree.mjs remove --repo <repo> --task <id>`.
It refuses remaining ignored files, changed worker patches, and patches no
longer represented in the destination. No automatic forced cleanup of those
files is supported. Preserve work and leave the directory in place if unsure.
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