Personal operator layer. /op:go routes any ask; /op:spec /op:plan /op:build run the scaled gate for features; /op:ship /op:sync /op:show /op:release run the daily ops. Every command ends with proof.
★not rated 2 1mo agoA
tokens not measured
originalMIT
A Jedi council for your codebase: 14 role-specialist agents, 24 domain commands (a11y, perf, QA, security, threat-modeling, SRE, ADR, cost tracking, MCP auditing), 11 skills including token economy, and a SQLite-backed learning crystal that compounds your corrections across sessions.
★not rated 2 4mo agoA
tokens not measured
originalMIT
Helps Claude make deterministic, auditable choices about which agent and skills to use for a given task — replacing prose-scanning agent/skill selection with a typed scoring kernel.
★not rated 2 yesterdayA
tokens not measured
originalMIT
The Forge: a guided pipeline from idea to shipped product — calibrated process, verified research, clickable decisions, checked builds, honest kill lines — plus a cross-project memory that compounds. Cross-tool (Claude Code, Cursor, Codex, Gemini, Hermes).
★not rated 2 1mo agoA
tokens not measured
originalMIT
Skill for talking to the Lattice agent-threading server ("Slack for agents"): register an identity, post/reply to threads, and poll notifications instead of ad-hoc file polling.
★not rated 2 7d agoA
tokens not measured
originalMIT
Turn the message you just typed in Claude Code into a reusable slash command — verbatim, optimised, reshaped, or parameterized — and list what you've saved.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Intelligence layer for Claude skills. Maintains a trust-rated catalog (curated + GitHub topic search), recommends what fits your project, returns ranked lists with pros, cons and customization advice, persists every decision, and migrates skills across 55 supported agent platforms. Ships in three editions: Lite…
★not rated 2 21d agoA
tokens not measured
originalMIT
163 specialist agent personas + 24 routing skills + 16 NEXUS strategy playbooks + 2 hooks. Fork of msitarzewski/agency-agents with China-market agents excluded and Korean + Japanese Business Navigators added. Installable two ways: as a user-level config bundle via scripts/install.ps1, or as a Claude Code plugin via…
★not rated 2 3mo agoA
tokens not measured
originalMIT
Ask, plan, delegate, verify, ask again. Turns requests into verified work: one capped question round, a plan.md as the contract, slice-scoped delegation, command-first verification, and learnings you approve.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Two-agent autonomous loop (Builder + Reviewer) for shipping multi-phase coding deliverables end-to-end without mid-run human input — finished work on an isolated harness branch with a PR opened back to the source branch.
★not rated 2 3mo agoA
tokens not measured
originalMIT