legion-deepseek-mode

Optional Legion code-intelligence diagnostics. Runs repo-native TypeScript and Pyright checks, filters changed-file diagnostics, emits legion.code-intel.v1 artifacts, and can append legion.span.v1 telemetry for benchmarkable pre-PR gates without making LSP servers a core dependency.

1 skill

The Codex-primary routing guide for Legion. Keeps the active primary inline where it has context and routes bounded work by configured archetype and model role, rather than treating another harness as the default secondary. Also maps Codex-native MCPs, mirrored skills, and bridged commands/agents.

1 skill

The routing guide for a Hermes-primary Legion session. Hermes can work inline as a registered coding family and use a metered, isolated `legion-delegate run --executor <different-harness>` handoff for independent implementation, review, and tie-breaks. Triggers when Hermes or one of its cron jobs / skills needs to build, fix, test, review, or delegate code work.

1 skill

See everything Legion does and close the self-learning loop. Unified legion.span.v1 telemetry, legion-report cost/success/latency, legion-bench deterministic repeated gates, legion-self-learn evidence/proposals, review-only legion-improve draft PRs, legion-trace, legion-otel-export, and legion-doctor verification.

1 skill

The decision guide for an opencode-primary Legion session. Keeps the active primary inline where it has context and routes bounded work by configured archetype and model role, rather than assuming a default secondary harness.

1 skill

Legion's dynamic multi-model orchestrator: the active primary decomposes work, configured executor roles fan out scoped slices, independent roles cross-verify, and the primary synthesizes and gates. Ships `legion-fanout` plus the LEGION_ULTRACODE max-exhaustive workflow.

1 skill

DeepSeek model harness with focused agents, commands, and skills for swarm-backed reasoning workflows

2 skills · 1 command · 1 agent

Delegates dbt and warehouse work to altimate-code, a specialized CLI agent with 100+ purpose-built data tools (SQL analysis, column-level lineage, dbt build/test/run, warehouse profiling, FinOps, connectivity to Snowflake, BigQuery, Redshift, Databricks, Postgres, MySQL, DuckDB).

2 skills · 4 commands · 1 agent · 1 MCP server · hooks

Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.

85 skills · 20 commands · 19 agents · 1 MCP server · hooks

Use Codex from Claude Code to review code or delegate tasks.

3 skills · 8 commands · 1 agent · hooks

Founder-mode executive team plugin: 13 cs-* C-suite agents (CFO, CMO, CRO, CPO, COO, CHRO, CISO, Chief of Staff, General Counsel, Chief Data Officer, Chief AI Officer, Chief Customer Officer, VP of Engineering) with distinct cognitive voices, plus 21 /c-level-agents:* slash commands — forcing-question office hours (CFO/CMO/CPO/CRO/CTO/CISO/GC/CDO/CAIO/CCO/VPE reviews), strategic sprint pipeline (brief → boardroom → decide → execute → post-mortem), and meta routing (/c-level-agents:founder-mode auto-router, /cs-onboard, /c-level-agents:cross-eval multi-model consensus, /c-level-agents:freeze cooldown lock). Wraps the 33 c-level skills with cognitive gearing, persona voice, and artifact-driven handoffs. The business-domain answer to YC Garry Tan's gstack.

22 skills · 13 agents

当用户希望将任务交给员工或协作者并跟进结果时，结合本地人员资料选择负责人，写清要求、协商工期、提供帮助并验收汇报；有飞书 CLI 时派单、读取回填和回复，缺少工具或权限时交付可转发文字。支持事件队列与可配置 Agent 接入，不承担招聘、绩效排名或惩罚。

1 skill