caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Curation, recall strategy, auditing and operations for the agent-memory MCP server backed by DynamoDB vector search.
Plugin agent-memory from marketplace agent-memory in dmux/aws-dynamodb-search-vector-rust-example. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
agent-memory-devContributing to the agent-memory Rust workspace — the hexagonal dependency rule, which crate a change belongs in, how to add or change an MCP tool, and the non-obvious invariants that have tests guarding them. Use when editing any crate in this repo, adding a memory operation or MCP tool, or reviewi
agent-memory-opsDeploy, wire and troubleshoot the agent-memory stack — Terraform, the Lambda build, the DynamoDB vector index, IAM for callers, the MCP client wiring, and what each failure symptom actually means. Use when deploying or destroying the stack, when memory tools fail with 403/401/credential errors, when
memory-auditInventory and clean a long-term memory store that has no list endpoint — sweep it with probe queries, cross-check the local write journal, and find duplicates, contradictions, stale entries and leaked secrets. Use when the user asks what is stored about them, wants memory cleaned up or exported, sus
memory-curationHow to decide what goes into long-term memory and how to phrase it. Use whenever storing something with memory_remember, when the user says "remember this", "save that", "don't forget", when a session produced a durable decision or preference worth keeping, or when deciding whether something is wort
memory-recallHow to search long-term memory well — when to call memory_recall and when to hold back, how to phrase a semantic query, how to read cosine distances, and how to treat what comes back. Use when recalling stored context, when the user refers to something from a previous session, or when tuning top_k,
/agent-memory:memory-auditInventory the memory store and report duplicates, contradictions, stale entries and leaked secrets
/agent-memory:memory-bootstrapLoad relevant long-term memory for the work about to start
/agent-memory:memory-doctorDiagnose the whole agent-memory path — binary, config, credentials, deployment, and a live round trip
/agent-memory:memory-saveCurate this session into long-term memory — extract, dedupe, store
/agent-memory:memory-setupBuild the MCP server and wire .mcp.json to the deployed API
memory-architecture-reviewerUse this agent to review changes to the agent-memory Rust workspace against its architectural invariants — the hexagonal dependency rule, the identity and tool-description guarantees, the vector-search correctness traps. Triggers include reviewing a diff or PR in this repo, adding or changing an MCP
memory-auditorUse this agent to inventory and health-check the long-term memory store. Triggers include the /memory-audit command, the user asking "what do you remember about me", requests to export, clean up or prune memories, and suspicion that a stored memory is wrong, stale or duplicated. Sweeps the store wit
memory-curatorUse this agent to review a conversation and store what deserves to outlive it in long-term memory. Triggers include the /memory-save command, the user asking to "save what we learned" or "remember this session", and the end of a session that produced durable decisions, preferences or constraints. Ru
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/journal.py"
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.