Orchestrates specialized agents to autonomously implement entire features end-to-end
Skill Claude CodeCodex
Explain how a subsystem, feature flow, or code path works, at the level a senior engineer onboarding onto it needs: architecture, runtime flow, where things live, and the gotchas. Simple questions are answered inline; complex ones fan out parallel read-only explorers and synthesize their traces into one coherent…
Skill Claude CodeCodex
Apply when dispatching research, scouts, or verification helpers. Hand the investigator the question, never the wanted answer — an investigator that knows the conclusion anchors to it and verifies nothing.
Skill Claude CodeCodex
Apply when writing any loop, retry, or watch cycle. Declare the cap with the loop and make hitting it a loud, terminal, reported outcome — never silent grinding. Size budgets are the output-side instance.
Skill Claude CodeCodex
Apply when designing an agent, subagent, or dispatch boundary. Keep complexity inside the worker and the seam narrow: declared inputs in, one bounded output back.
Skill Claude CodeCodex
Apply when issuing any verdict, claim, or completion report. Cite the evidence that proves it — a command run, a file:line, a re-queried value — or degrade the verdict and say so.
Skill Claude CodeCodex
Apply before any irreversible act — merge, force-push, close, delete, publish. Fire only on stated intent, scope one approval per irreversible mutation, and never re-ask what was granted.
Skill Claude CodeCodex
Apply when a guarantee cannot be evaluated. The answer is no: unknown counts as unsupported, a missing verdict as not passed, an inconclusive refutation as the finding standing.
Skill Claude CodeCodex
Apply when passing state between steps, agents, sessions, or runs. Write the durable artifact to disk and treat the file as the interface; never rely on conversation memory.
Skill Claude CodeCodex
Apply when debugging any failure. Trace each symptom to its root cause and fix it there — reproduce first, ask why until the causal chain bottoms out, and never add a guard that silences the symptom while the disease remains.
Skill Claude CodeCodex
Apply when work is judged — a review, a verdict, a verification pass. Never let the generator grade its own work; give the evaluator fresh context and veto without authorship.
Skill Claude CodeCodex
Apply when deciding whether to consult the user mid-run. The human decides what to build and what to ship; everything between runs autonomously and defers findings to the PR review.
Skill Claude CodeCodex
Apply when a procedure can be interrupted or repeated. A re-run converges on the same end state: already-done is done, match before create, re-read before write.
Skill Claude CodeCodex
Apply when granting tools, credentials, or environment to any role or child process. The toolset is the guarantee: enforce a constraint by withholding the capability, not by asking for restraint.
Skill Claude CodeCodex
Apply when a rule must hold reliably. Enforce it with a deterministic check at the cheapest layer that can catch it, never with a prompt instruction alone.
Skill Claude CodeCodex
Apply when any externally sourced value approaches a shell command. Prose travels by file, stdin, or the environment; scalars pass a byte-exact allowlist; everything is captured, guarded, and used in one invocation.
Skill Claude CodeCodex
Apply when a procedure waits on something outside the session — CI, a reviewer, a vendor CLI, a long job. Spend the wait in one backgrounded call the harness reports on, never in foreground sleeps that occupy the turn.
Skill Claude CodeCodex
Apply when wiring an enhancement path — a sub-agent, a second-vendor pass, an upload. It improves the work when it runs and costs nothing when it cannot: skip loudly, fall back inline, never soften the outcome.
Skill Claude CodeCodex
Apply when mutations need user approval. Write the plan down, present each consequential choice with one recommendation, and execute only the answered subset — a mutation executes on the user's answer, or on an item clearing the verified-confidence carve-out.
Skill Claude CodeCodex
Apply before any destructive or history-rewriting step. Capture the baseline that classifies the after-state and the pre-image or anchor that makes the change recoverable — no pre-image, no destructive write.
Skill Claude CodeCodex
Apply when executing any procedure with two or more ordered steps. Seed one todo item per step before starting and mark each complete as you go; the context running the procedure owns its own ledger and never merges it upward.
Skill Claude CodeCodex
Apply when an autonomous step hits an open question. Resolve it yourself, mark it as an explicit auditable assumption naming the rejected alternative — an unmarked guess is a defect.
Skill Claude CodeCodex
Apply when executing against an approved plan, structure, or anchored change. The artifact authorizes exactly the change it names; work outside the fence is documented, never done silently.
Skill Claude CodeCodex
Apply when a rule, constant, or schema could live in two places. Define it in exactly one, name that owner, and make every other surface consult it rather than restate it.
Skill Claude CodeCodex
Apply when reporting any run's outcome. What did not happen is reported as visibly as what did — skipped passes, degraded modes, and deliberate omissions each get a named line.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: