Skill Claude CodeCodex
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
Skill Claude CodeCodex
Release a validated Open Harness commit by pushing it to main or master, then monitor the automatic SemVer/GHCR/GitHub Release workflow. TRIGGER when: asked to release, version, ship, cut a release, or verify release artifacts.
Skill Claude CodeCodex
Render an artifact (or in-context material) as a bespoke, self-contained HTML file for one-shot human consumption. Writes to ephemeral scratch under $TMPDIR — these are consumption artifacts, not source, and nothing under .oh/ persists them. TRIGGER when: asked to render HTML, generate an HTML report, visualize an…
Skill Claude CodeCodex
Scientific session-closing retrospective: scan the current conversation, turn each signal into a falsifiable hypothesis, cite session evidence for AND against it, assign a verdict (supported / refuted / inconclusive) and a confidence level, then nominate only supported, sufficiently-confident hypotheses as candidate…
Skill Claude CodeCodex
Context-as-environment decomposition (Layer B of the RLM integration). Treat a large artifact (file / dir / log) as a REPL/filesystem the root agent greps and slices instead of ingesting — partition it into addressable chunks via query-context.mjs --map, RECURSE sub-agent calls over the relevant chunks under a bounded…
Skill Claude CodeCodex
Canonical decomposed build workflow and dispatcher. Routes the first token of $ARGUMENTS to one of three subcommands: plan, execute, or retro. Each is pointed at a .oh/tasks/ / folder (the universal interface) and is independently runnable and fan-out-able. This skill owns the ONLY build path; there is no all-in-one…
Skill Claude CodeCodex
Write and rewrite technical prose in Simplified Technical English style: short declarative sentences, active voice, imperative procedures, one term per concept, no hedges, and explicit conditions. Never simplifies code, commands, identifiers, paths, or quoted literals. Marks missing values with a placeholder rather…
Skill Claude CodeCodex
Spawn 5 domain experts to propose roadmap items, then an AI council drafts a roadmap, a Strategic Critic challenges it, and the council finalizes with revisions. Updates the pinned roadmap issue. TRIGGER when: asked to build roadmap, prioritize features, strategic proposal, "what should we build next", or rank product…
Skill Claude CodeCodex
Dispatcher for bidirectional origin↔upstream harness sync — routes the first token of $ARGUMENTS to one of three subcommands: publish (origin→upstream), catchup (upstream→origin), or status (read-only direction check). The canonical topology and intentional divergences to preserve live in references/topology.md. Full…
Skill Claude CodeCodex
Start, inspect, or stop T3 Code (npx t3) in the Open Harness sandbox. Use this for the browser-based T3 Code harness on port 3773, including tmux launch, pairing URL discovery, logs, status, and shutdown. T3 Code wraps an already-authenticated Claude Code, Codex, or OpenCode backend. TRIGGER when: user asks to run T3…
Skill Claude CodeCodex
Weighted-trajectory selection: sample N candidate trajectories for one task, attach deterministic signals to each, then weight + select among them with a pure, version-controlled scorer we own (score-trajectories.mjs) rather than a model black box. The Workflow tool's judge-panel / adversarial-verify patterns PROPOSE…
Skill Claude CodeCodex
Dispatcher for the harness wiki knowledge base — routes the first token of $ARGUMENTS to one of three subcommands: ingest, query, or lint. The corpus lives at .oh/skills/wiki/corpus/ (entity pages) and corpus/raw/ (immutable snapshots), owned by this skill and gitignored-by-default (curated entries are whitelisted…
Skill Claude CodeCodex
Manage .worktrees/ lifecycle: create worktree, list worktrees, remove worktree, clean worktrees, stale worktrees audit, isolate work, project clone. TRIGGER when: any git worktree operation, branch isolation needed, stale worktrees review, project clone under projects/ (e.g. "clone / to projects", "add to projects"…
Instructions file CodexOpenCode
Instructions for mifunedev/openharness, covering open harness — orchestrator, what open harness is, 1. agent work stays inside the sandbox, 2. coding-harness choice does not change the workspace and 3. remote and unattended operation are normal.
Instructions file
Instructions for mifunedev/openharness, a project described as: 🏗️ Run coding agents in a sandbox, not on your machine.