Skills and agents that add lifecycle gates around planning and building with Claude Code, with each kind of job running on its own model and effort: ground a plan in reality, verify a finished diff with fresh eyes, audit injected context, set up per-repo permissions so you can run auto mode with confidence, and turn a.
★not rated 3
changed 8d agoA
tokens not measured
originalMIT
Multi-model orchestration for Claude Code: the session model leads as tech-lead orchestrator, routing work across model-pinned executors (deep-reasoner/Opus, fast-worker/Sonnet, scout/Haiku) and a cross-vendor Codex peer — with a first-match routing table, delegation contracts, budget modes, an escalation ladder, and…
Paper-grounded ML research and open-problem attack for Claude Code. Crawls arXiv and citation graphs, reads whole papers in parallel subagents, mechanically verifies every quote, archives a model's real code locally and grounds later sessions in it, and runs falsifiable attacks on hard unsolved problems.
★not rated 3 2mo agoA
tokens not measured
originalMIT
Spec-driven development for existing codebases. Reads your repo's conventions, interviews you about a change, and writes spec, design and tasks to disk, with blast-radius analysis. Regulatory policy profiles are optional and off by default.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Code review, pre-flight, worktree isolation, guard hooks, and risk-weighted test coverage for Claude Code. Consumed as-is; /dotclaude:coding and /dotclaude:testing elicit your project's bar.
★not rated 1
changed 1mo agoA
tokens not measured
originalMIT
A collection of Claude Code skills for general software-engineering work — each a self-contained, named methodology you invoke by intent. terry (agent-fleet orchestration AND a producer-consumer task queue with backpressure — a long-running manager loop that drives parallel worker agents across isolated git worktrees.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Verify browser-based game features through a PM-driven QA loop. Ships a project-agnostic runner + adapter skeleton + journey schema so projects onboard by copy-and-adapt, not natural-language reconstruction. Six skills covering request → plan → execute → review → rollup, plus the bootstrap that drops the framework…
★not rated 1 5mo agoA
tokens not measured
originalMIT
Installs 'The Fable Way' working discipline, built for a frontier Claude model at medium-xhigh effort: an auto-triggering method skill (reflexes, risk tiers, plan shape, a calibrated-code stance) plus runner skills (scope, debug, adversarial review, verify, ship) that dispatch a capability-confined fable-lens reviewer.
★not rated 1 2mo agoA
tokens not measured
originalMIT
An always-on operating protocol for coding agents: build only what's asked, surface ambiguity as Q/A/P/E/X, scale process to task size, and verify before claiming. Injected into every session via a SessionStart hook.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Three-phase Claude Code Codex CLI collaboration workflow: Claude plans and writes the spec, a Claude subagent implements in the host working tree, a fresh Codex session adversarially reviews the diff. Implementation and review are never the same model. For code changes that deserve a written spec.
★not rated 1
changed 1mo agoA
tokens not measured
originalMIT
The open operating system for building an AI-native company: a Handbook, a Dictionary, and AI skills, flows, loops, and advisor agents spanning the whole arc - frame, architect, build, trust, ship, grow, defend. Theme-agnostic.
★not rated 1 3mo agoA
tokens not measured
originalApache-2.0