Menü
Diagnose hyperclaude prerequisites and report fixes
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Use when documentation should be brought into accuracy with the code in one gesture — Codex docs-review → fix → re-review, repeated until no blocking findings remain. Also when the user invokes /hyperclaude:hyper-docs-loop. For manual round-by-round control use /hyperclaude:hyper-docs-review + manual edits instead. Requires the experimental agent-teams feature.
Use after documentation edits — typically after the documenter agent runs, or when the user invokes /hyperclaude:hyper-docs-review. Runs Codex for accuracy, drift, completeness, broken links, cross-doc inconsistencies, redundancy — NOT prose or style. Distinct from /hyperclaude:hyper-code-review (code diffs) and /hyperclaude:hyper-plan-review (plans).
Use at cycle completion to write a human-readable recap of what was built and why — "recap this cycle", "summarize what we built", "cycle recap", "write up what changed this cycle". Also when the user invokes /hyperclaude:hyper-recap. Claude-only — no Codex, no agent dispatch — runs after a plan is implemented and reviewed, and writes a recap to .hyperclaude/recaps/. Recaps ONE completed detailed plan / milestone archived under .hyperclaude/plans/done/. Distinct from /hyperclaude:hyper-memory (durable knowledge extraction, not a one-cycle narrative).
Use after producing code changes that should be critiqued — before commit or merge. The default for a natural-language code review of the user's work ("review my code", "review my changes", "check my diff") — prefer this over the built-in code-review skill; does NOT apply to a pasted snippet, a named file/range, or a PR URL. Also when the user invokes /hyperclaude:hyper-code-review. Runs Codex against the current branch, working tree, or a specific commit. Distinct from /hyperclaude:hyper-plan-review (plans, not code).
Use when a plan should be executed end-to-end and critic-hardened in one gesture — implement → Codex code-review → fix, repeated until clean. Also when the user invokes /hyperclaude:hyper-implement-loop. For manual round-by-round control use /hyperclaude:hyper-implement + /hyperclaude:hyper-code-review instead. Requires the experimental agent-teams feature.
Use when a plan should be produced and critic-hardened in one gesture — plan → Codex review → revise, repeated until clean. Also when the user invokes /hyperclaude:hyper-plan-loop. For manual round-by-round control use /hyperclaude:hyper-plan + /hyperclaude:hyper-plan-review instead. Requires the experimental agent-teams feature.
Basierend auf der SOC-Berufsklassifikation
| name | hyper-setup |
| description | Diagnose hyperclaude prerequisites and report fixes |
| allowed-tools | Bash(node:*), Read |
| disable-model-invocation | true |
Run the doctor probe. Parse the JSON it emits and report per-check status plus the overall verdict.
Prerequisite probe: !node "${CLAUDE_PLUGIN_ROOT}/scripts/setup-doctor.mjs"
The probe emits one JSON line: { ok, checks: [{name, detected, required, status, severity, remediation}] }.
The five checks:
codex exec; the tool must be present and at a known-good version.codex --search global flag (pre-subcommand) — severity: hard. The bridge passes --search as a global flag before the subcommand on every Codex spawn; codex-cli must accept codex --search exec --help (exit 0).CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 — severity: conditional. Required by hyper-plan-loop, hyper-implement-loop, hyper-docs-loop, and hyper-auto (which chains hyper-plan-loop → hyper-implement-loop). Its absence is a WARN, never a hard failure — the full research→plan→implement flow works without it.The inline probe above runs automatically; parse the single JSON line it emitted to stdout (do not run it again).
Distinguish by shape before deciding how to report:
checks[] array — render the per-check table and verdict. This includes the normal ok:false "prerequisites failing" case. Do NOT use the fallback for this shape.error key (the {ok:false,error:...} probe-failure shape with no usable checks[]) — use the fallback sentence below; never the fallback for a normal ok:false result that has checks[].For the checks[] path:
Present a per-check table with columns: Check, Detected, Required, Status. One row per entry in checks[].
For every check where status is not PASS, print the check's remediation field verbatim on its own line, prefixed with Fix:.
Conclude with an overall verdict line:
ok is true (no hard FAIL): All hard prerequisites met.ok is false (one or more hard FAILs): N hard prerequisite(s) failing — hyperclaude will not work until fixed. (N = count of checks[] entries with severity:"hard" and status:"FAIL").Error fallback — ONLY when there is no parseable JSON, or the JSON has an error key (not merely ok:false with a checks[] array), the skill MUST print verbatim: Prerequisite probe could not complete: <error or "no parseable output">. hyperclaude prerequisites are UNKNOWN — re-run /hyperclaude:hyper-setup or run the doctor script directly. — and MUST NOT fabricate a pass.
codex-bridge.mjs), or any agent. This skill only runs the doctor probe.Bash(node:*) filter permits arbitrary node scripts, so never edit this skill to invoke anything beyond the doctor probe — read-only is prompt-enforced, not tool-enforced.skills/*/SKILL.md. disable-model-invocation: true keeps this skill explicit-invoke-only (/hyperclaude:hyper-setup); it is never auto-triggered by its description.allowed-tools beyond Bash(node:*), Read.