Typed, probability-carrying answers for the questions apex-dispatch and apex-scope-loop leave to judgment (task class, risk tier): one CLI, rubric files, a fail-closed validator for every backend, tri-state uncertainty, and calibration that only a measurement job can grant. Off until a repo opts in; absent, slow or unconfigured, routing stays table-only.
Plugin apex-decision-layer from marketplace apex-dev-skills in Skobyn/Apex-Dev-Skills. Commands read from the repo's manifest — 16 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
decision-rubricWrite, review or version a decision-layer rubric (rubrics/<id>@<v>.json) — the questions apex-decide asks a backend, their labels, the state allowlist, uncertainty thresholds, hard rules and the data-handling clause. Use when adding a rubric for a new consumer, when `apex-decide lint` fails, or when
/apex-decision-layer:decideAsk the decision layer one rubric question and explain the envelope — verdict, probabilities, uncertain, calibrated and why, or the unscored reason. Pass a rubric id and a JSON state as $ARGUMENTS, e.g. `risk-tier@1 {"changed_paths":["src/auth/session.py"],"changed_lines":40,"changed_files":1,"task_
/apex-decision-layer:doctorCheck this repository's decision-layer setup — config, egress, the backend per rubric, whether each hosted backend's API key is present (never its value), the rubrics, and with `--probe` whether jev and frontier are reachable. Pass `--probe` as $ARGUMENTS to send one empty, free request to each host
/apex-decision-layer:labelRecord a human label for one past decision — the class or tier you would have chosen with hindsight — in .claude/apex-decision-layer/labels/. Pass "<rubric>@<v> <decision_id> <label> [note]" as $ARGUMENTS. Refused while an apex-scope-loop run is active.
/apex-decision-layer:lintLint decision-layer rubric files against the authoring rules (condition not conclusion, no counting words, a none label, untrusted fields declared, data-handling clause) and print each rubric's question_hash. Pass rubric file paths as $ARGUMENTS, or nothing to lint every shipped rubric.
/apex-decision-layer:measureMeasure one rubric and backend against this repository's labels — AUROC with its CI beside Brier and ECE, ablation arms, the threshold sweep, and a status (insufficient n, degenerate, fails or passes the kill criterion). Pass "<rubric>@<v> <backend> [--outcomes FILE]" as $ARGUMENTS. Never locks a re
bash "${CLAUDE_PLUGIN_ROOT}/hooks/shadow-hook.sh" done-claim
bash "${CLAUDE_PLUGIN_ROOT}/hooks/shadow-hook.sh" tool-risk
Route and govern delegation: a compiled routing policy picks the tier, provider, fan-out and review shape for each task or ad-hoc ask; PreToolUse/SubagentStop hooks enforce it; provider shims run external workers; every route, spawn, worker run and verdict lands in a hash-chained ledger, which report.sh --per-task prices per routed task. Drives apex-scope-loop as its execution engine.
2 skills · 6 commands · 10 agents · hooks
Routing and gate engine for apex-app: lanes + surface-ledger routing, cross-platform guardrails, and phases that close on computed obligations.
2 skills · 4 commands · hooks
Decide -> plan -> loop: SPARC-shaped ADR + phased plan authoring with scope sizing (bugfix, poc, feature) and an intent round, autonomous /loop + /schedule execution, per-phase swarm dispatch, The Gibson's harness gates (baseline green gate, independent review, Tier-C human approval), and an operate phase that watches landed plans against their declared checks.
2 skills · 3 commands · 2 agents
Trace, replay, and cost-attribute multi-agent runs: hook-driven JSONL AgentTrace, deterministic OrchestrationReplay, and per-subagent TokenLens — pure artifacts, with an optional read-only MCP dashboard server.
3 skills · 1 command · 1 MCP server · hooks
Interview-first greenfield project initializer: opens with 'what are you trying to build?', researches the context, then scaffolds a fully-governed repo (paved-road defaults), provisions the Apex-Dev-Skills suite (plus optional ruflo), and verifies it before the first commit. Generated projects are steered to build features via apex-plan/apex-loop. Supports TypeScript/JavaScript, Python, Go, and Rust.
3 skills · 1 command · 1 agent
Tool-contract validation + runtime reliability: a PostToolUse ledger that infers per-tool schemas and flags contract drift, plus FlakeGuard detection of non-deterministic agent failures (retries, partial failures, flaky tools).
2 skills · 1 command · hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.