Cross-model council — assess the models reachable via locally installed peer agentic CLIs (codex, agy, opencode) against a standardized problem stack, cast them into a roster, and run cross-model fan-out plays (v1: Diff+Synthesis) chosen per project. Built on a unified delegation contract with graded permission postures; in-session and uncontainerised, distinct from sdlc-workflows' Archon/Docker/DAG delegation
Plugin sdlc-model-council from marketplace ai-first-sdlc in SteveGJones/ai-first-sdlc-practices. Commands read from the repo's manifest — 1 month ago.
council-policyPolicy for the cross-model council: when to hand off to an installed sibling plugin's own slash command (`/codex:*`) versus dispatching our `delegation-runner` (backend: codex|agy|…), which backend to pick, what permission posture to use, and the fan-out/cost discipline that applies regardless of ba
/sdlc-model-council:backendsList registered delegation backends, whether each is installed/authenticated, and any sibling plugin available for it.
/sdlc-model-council:council-assessRun the standardized problem stack across models under a budget cap — free calibration wave first, then paid waves, then a roster + diversity map.
/sdlc-model-council:council-commissionOnboard this project onto the model council — discover the reachable fleet, characterize the repo, audition at the chosen depth, then write the roster + policy + commission record.
/sdlc-model-council:council-estimateToken-free pre-dispatch cost estimate for a council assessment — per-model cost table and total, no models called.
/sdlc-model-council:council-rosterInspect the project's council roster — grades, roles, provisional flags, cost, and the diversity map's most/least decorrelated model pairs.
/sdlc-model-council:council-runRun a cross-model fan-out play (v1: Diff+Synthesis) on a task — cast a decorrelated panel from the roster, fan out to N models, and return one attributed synthesis with a baseline delta.
/sdlc-model-council:delegateDelegate a scoped sub-problem to an external agentic CLI backend (codex, agy, …) and get a compact result back.
council-judgeSynthesises a cross-model fan-out into one attributed verdict for the Diff+Synthesis play (and future consensus/best-of-N/gen↔verify plays) of the sdlc-model-council plugin. Reads the anonymised response bundle a play produced on disk (combine/blind-bundle.md) plus the shared task (task.md) and retu
delegation-runnerDelegates a scoped sub-problem to an external agentic CLI backend (`codex` — OpenAI/GPT, `agy` — Antigravity/Gemini, and any future backend registered as a one-directory adapter under scripts/adapters/) and returns a compact result — the full peer-agent transcript stays on disk under ./tmp/model-cou
Filesystem-based project knowledge base — librarian agent, hash-tracked indexes, cross-library queries with priming + synthesis, audit log, parallel map-reduce bulk ingest, ingest/query/lint operations
16 skills · 4 agents
Containerised delegated execution — Archon DAG workflows with team-scoped Docker containers, tiered termination, 4 bundled workflows, 6 skills
6 skills · 10 commands · 1 agent
Core SDLC rules, validators, enforcement, and workflows
9 skills · 4 agents · hooks
AI/ML specialist agents — architects, prompt engineers, RAG designers
14 agents
Android development — Material Design 3, Compose, app architecture, Gradle, Play release & performance agents + scaffold/signing/play-release skills & Play pre-flight checks (pairs with sdlc-team-mobile)
4 skills · 6 agents
Web full-stack agents — frontend, backend, API, data, DevOps, UX & integration architects
9 agents
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Use the JFrog Platform from Claude Code: Artifactory repos and artifacts, security findings and exposures, Catalog package safety and downloads, workflows across the SDLC, and platform administration.
7 skills · 1 MCP server · hooks
33 C-level advisory skills (install the separate companion c-level-agents plugin for the persona layer): virtual board of directors (CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO) plus General Counsel, CDO, CAIO, CCO, and VP of Engineering (DORA delivery throughput analyzer, engineering hiring funnel calculator with conversion + pipeline gap, eng team structure designer with squad/tribe + manager-trigger), executive mentor, founder coach, orchestration (Chief of Staff, board meetings, decision logger), strategic capabilities (board deck builder, scenario war room, competitive intel, M&A playbook), culture frameworks. The 13 cs-* persona agents + 21 /c-level-agents:* slash commands (founder-mode router, office-hours intake, multi-role boardroom, strategic sprint pipeline, cross-model consensus, cooldown freeze) ship in the companion c-level-agents plugin.
34 skills · hooks
Full-lifecycle SDLC orchestrator: a 12-stage pipeline (SRS, architecture, spec, plan, build, eval, deploy, monitor, release) driven by specialized agents, persistent cross-session memory, auto-reflection, gate enforcement, and semantic skill mining that proposes new skills from recurring workflows.
45 skills · 27 agents · hooks
Standalone model routing and one-off handoffs with Claudex Route, plus the full Claudex Loop planning, build and review workflow.
6 skills
Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code + Codex CLI) for multi-perspective exploration, then synthesizes findings into actionable optimization plans. Supports self-audit, UX audit, API audit, architecture review, and competitive benchmarking via competitors-analysis skill
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.