privacy
claudeRefuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity.
Memory for Claude Code and Codex. It keeps a record of its conversations, turns them into memories it recalls in later sessions, and keeps corrections attached to what they corrected. Runs on your machine. Requires your own Anthropic API key.
Plugin entity from marketplace anchor in tpac/entity. Commands read from the repo's manifest — 6 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
architecture-reviewReview the architecture of a subsystem or cross-file concern in a codebase. Use for questions about ownership, placement, coupling, duplicated responsibilities, consolidation, or a subsystem refactor plan. Trace callers and contracts, verify prior brain decisions, and recommend keeping the structure
brainThe identity stance — how the entity reaches into its brain (recall, recognition, revision). The body below is injected at every session boot by the daemon; invoke `/brain` only to re-read it mid-session, e.g. after context loss. For tool signatures and field reference, see references/detailed-api.m
dashboardOpen the brain dashboard — the observer UI (graph, traces, live decode/encode, sessions, logs) served locally at http://localhost:47303. Invoke `/dashboard` (`/entity:dashboard`) to make sure it's running and open it in the browser. Use whenever the operator says "open / show / launch the dashboard"
self-salvagePreserve a strong start for the next session on the same work when an arc closes, context grows heavy, or the operator asks to salvage, hand off, continue in a new session, or fork. Reconcile durable knowledge, preserve useful working material, and prepare or deliver a retrievable handoff using the
shape-reviewMechanism-level review of a diff or a plan: is the mechanism chosen the simplest one that satisfies the requirement, and does it fix the class of problem or one instance of it? Licensed to propose a different behavior-equivalent implementation. Runs after a fix is written (or on the stated plan befo
watchFind, inspect, message, and coordinate with parallel sessions of the same entity across Claude Code and Codex. Use for cross-session requests and /watch; choose a supported host-specific return path when asked to remain reachable between prompts.
brainruns: ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/mcp-launch.sh
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/boot-brain.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pre-response-recall.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pre-edit-suggest.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/post-response-track.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stop-failure-log.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-end.sh"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/post_tool_trace.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/post_tool_trace.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/post_tool_trace.py"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/worktree-context.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/worktree-cleanup.sh"
Refuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity.
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server
3 skills · 1 command · 1 agent · 1 MCP server
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
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.