guild
01Plugin Claude Code
Guild marketplace for Claude Code plugins focused on specialist agent teams, durable memory, and evidence-based evolution.
Plugin Claude Code
Guild marketplace for Claude Code plugins focused on specialist agent teams, durable memory, and evidence-based evolution.
Plugin Claude Code
A team-of-specialists plugin for AI coding hosts: 15 domain specialist type templates across engineering, content, and commercial groups (minted into your project on demand) plus 3 machinery agents, the v2 single-verb lifecycle (init · ideate · plan · build · qa · ops), a categorized wiki with decision capture, and a…
Agent Claude Code
Authors Guild plugin slash commands (commands/.md). Handles command argument parsing patterns, skill delegation, help text, and registration metadata. TRIGGER when a new /guild or /guild: slash command is needed, when an existing command's arguments/help need updating, or when a command must be re-wired to a new…
Agent Claude Code
Authors and reconciles Guild plugin in-repo documentation (README.md, CONTRIBUTING.md, CHANGELOG.md, AGENTS.md/CLAUDE.md prose sections) and updates website-pointing links when the canonical docs site changes. The plugin no longer carries a docs/ set — docs/ holds only a static redirect page + assets. The primary…
Agent Claude Code
Authors cross-cutting Guild plugin tests under tests/ — trigger-accuracy evals, wiki-lint fixtures, end-to-end regression specs, paired-eval harness tests, boundary-collision evals. TRIGGER when cross-cutting test fixtures or eval harnesses are needed, when regression coverage must be added at a phase gate, or when…
Agent Claude Code
Authors Guild plugin hooks. Owns hooks/hooks.json plus hook scripts — bootstrap.sh, check-skill-coverage.sh, capture-telemetry.ts, maybe-reflect.ts — and the agent-team handlers TaskCreated, TaskCompleted, TeammateIdle. TRIGGER when a new Claude Code hook event needs wiring, when a hook script needs to be written or…
Agent Claude Code
Lays down Guild plugin scaffolding (.claude-plugin/plugin.json, marketplace.json), repo-root CLAUDE.md, and top-level directory structure per the canonical repo layout. Runs end-to-end integration dogfood at each phase boundary and cuts phase tags. TRIGGER when starting a new plan phase, setting up plugin manifests…
Agent Claude Code
Dev-team specialist for harvesting durable knowledge from Guild's own research/ideation corpus (.guild/research/ and the workspace self-build knowledge base) into recallable canonical pages. Distinct from the shipping guild:researcher (which writes end-user research deliverables) — this agent owns the SELF-BUILD path…
Agent Claude Code
Dev-team specialist for security audits of Guild's own publishing surface — .gitignore policies, share-policy enforcement, scrub spec review, secrets-grep tuning, pre-flight leak audits for any commit that newly tracks content. Distinct from the shipping guild:security (which threat-models end-user products) — this…
Agent Claude Code
Authors Guild plugin skills across Tiers 1-5. Writes skill bodies, YAML frontmatter (name, description, whentouse), per-skill evals.json, and runs description optimization so every skill stays ≤ 1024 chars with ≥ 3 trigger phrasings. TRIGGER when a new skill is needed under skills/core/, skills/meta/…
Agent Claude Code
Authors the Guild specialist role definitions — the 2 machinery agents under agents/.md and the 15 domain type templates under templates/specialists/.md. Writes pushy TRIGGER / DO NOT TRIGGER blocks, frontmatter (name, description, model, tools, skills), and role body guidance. Runs adjacent-boundary scans when new…
Agent Claude Code
Authors Guild plugin TypeScript/Node tooling. Owns scripts/ (evolve loop, flip report, description optimizer, rollback walker, shadow-mode harness) plus .mcp.json and the optional MCP servers mcp-servers/guild-memory/ and mcp-servers/guild-telemetry/. TRIGGER when a utility script, MCP server, or .mcp.json wiring is…
Skill Claude CodeCodex
Assembles per-specialist 3-layer context bundle: Universal (400 tokens — guild:principles + project-overview + goals) + Role-dependent (800–1500 — standards + 2–4 entity pages matching role) + Task-dependent (800–1500 — lane from plan + named refs + upstream contracts + active decisions). Target 3k tokens, hard cap…
MCP server Claude CodeCodexCursor +2
MCP server "guild-memory" as configured in lookatitude/guild. Runs ${CLAUDE_PLUGIN_ROOT}/mcp-servers/guild-memory/dist/index.js with node.
MCP server Claude CodeCodexCursor +2
MCP server "guild-telemetry" as configured in lookatitude/guild. Runs ${CLAUDE_PLUGIN_ROOT}/mcp-servers/guild-telemetry/dist/index.js with node.
Instructions file CodexOpenCode
Instructions for lookatitude/guild, covering guild — repo orientation, where things live, v2 phase → skill dispatch, dev team (.claude/agents/) and project-local state.
Instructions file
Instructions for lookatitude/guild: Claude Code reads CLAUDE.md; Guild keeps the actual host-neutral directions in AGENTS.md so every host sees the same rules.
Agent
The on-demand powerful supervisor a stuck low-tier agent consults. Answers EXACTLY ONE escalated sub-question, seeing only the draft + question + a compact critique instruction — NEVER the raw file/project context (that withholding keeps the call cheap). Returns a guild.handoff.v2 envelope; the cheap/mid agent…
Agent
The mid-tier installed machinery agent that ASSEMBLES bounded context and emits run-scoped capability evidence — the executor for Learn's semantic operations and for per-lane context bundles, so a project-local role is never also the thing that assembles its own context. Writes ONLY under .guild/context/…
Agent
The generic mid-tier task-lane implementer: takes a settled plan lane and writes/refactors its code (draft, reason, build), escalating to the advisor when above its tier. The default ephemeral worker for implementation lanes that are NOT domain-recognizable. TRIGGER for "implement this lane", "build this task", "write…
Command
Self-maintenance — static security audit of installed Guild scripts (SHA-256 hashes, network/filesystem flags) + the static boundary-check section. Read-only static analysis. Dispatches to guild:audit.
Command
Development — context-assemble + dispatch lanes. Backend (agentmode/tmux) is resolved once at intake via the run-start preflight snapshot — not selected per-phase. Snapshot effective.agentmode drives lane dispatch (team / agent / subagent).
Command
Manage the project config surface .guild/settings.json — the single JSON file holding every Guild option (rigor, review/adversarial, host, agentmode/tmux dispatch ladder, auto-approve gates, loops, quality budgets, wiki, per-run role pins). config init (= reconcile sync) scaffolds it fully-documented and…
Command
Launch the local benchmark web dashboard over this project's runs + knowledge (runs table, knowledge-graph explorer, wiki browser). Resolves the benchmark checkout, serves on a free local port, bulk-imports the project's run logs, prints the URL. No network I/O without explicit confirmation (--install). Dispatches to…