openltm

Plugin openltm from marketplace OpenLtm in RohiRIK/OpenLtm. Commands read from the repo's manifest — 12 days ago.

Skills (7)

• agent-trust-boundaries

  USE WHEN separating trusted instructions from untrusted content or tool output.

• command-path-safety

  USE WHEN hardening command execution, path handling, or installer boundaries.

• secret-safe-handling

  USE WHEN handling credentials, env vars, logs, tests, or docs safely.

• GitLearn

  Mines durable LTM memories from past git commits through the git-learner agent (no API key needed). Use when the user says 'learn from our git history', 'mine the last N commits', 'backfill memories since <date>', 'onboard this repo into LTM', or wants to harvest patterns after a sprint.

• Ltm

  OpenLTM long-term memory: tool names, the recall-before / learn-after ritual, categories, project context, and what the hooks already inject. Use when the user says 'remember this', 'save this gotcha', 'what do we know about X', 'did we decide on Y before', 'forget that memory', 'link these memories

• MemoryReview

  Curation pass over OpenLTM memory: triage pending session-end proposals, stale-flagged memories, conflicting or superseded entries, and low-value duplicates, then accept, revalidate, relate, or forget them with the user's approval. Use when the user says 'review memories', 'clean up memory', 'curate

• Spec

  Writes a grounded spec: recalls prior decisions from LTM, explores the affected code, then writes testable acceptance criteria to specs/<feature>.md. Use when the user asks to 'spec this', 'write a spec', 'define what to build', or 'write requirements / acceptance criteria' before planning or implem

Slash commands (8)

• /openltm:admin

  USE WHEN running schema migrations, scanning memories for secrets, or querying the memory audit log. Groups migrate | scan | audit. (The graph server moved to /openltm:server.)

• /openltm:analyze-context

  USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.

• /openltm:doctor

  USE WHEN OpenLTM is down or misbehaving: the MCP server will not start, memories are not injected, hooks fail, or a migration error (such as a checksum mismatch) blocks the database. Read-only diagnostic with a fix line for every failed check.

• /openltm:health

  USE WHEN checking memory health, reviewing project scores, inspecting janitor status, or diagnosing why memories are decaying. Shows health scores, decay summary, activity log, and log health.

• /openltm:memory

  USE WHEN recalling past decisions, storing new insights, forgetting stale memories, linking memories, or reviewing pending memory proposals. Groups recall | learn (with optional --save-context) | forget | relate | propose.

• /openltm:onboard

  USE WHEN setting up LTM for a new project, diagnosing hook or plugin issues, or running first-time setup. Runs the onboarding wizard with doctor checks.

• /openltm:project

  USE WHEN initializing a project goal, analyzing project context before starting work, or registering a project in the LTM registry. Groups init | analyze | register.

• /openltm:server

  Start, stop, or check the OpenLTM graph visualizer (UI on localhost:7332, API + WebSocket on localhost:7331). USE WHEN the user wants to open, launch, stop, kill, or check the memory graph server.

Subagents (2)

• git-learner

  Mines durable engineering memories from git commit diffs and stores them in LTM. Use to onboard a repo, backfill history after enabling gitLearn, or harvest patterns after a sprint. Reads diffs in its own context so raw git output never reaches the main thread.

• ltm-planner

  Plans a feature, refactor, or architectural change when prior decisions stored in OpenLTM long-term memory matter — recalls and traces those decisions itself (read-only), then returns a step-by-step plan for confirmation. Use when the user asks for an implementation plan in an area with past decisio

MCP servers (1)

• memory

  runs: bun run ${CLAUDE_PLUGIN_ROOT}/src/mcp-server.ts

Hooks (7)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/src/SessionStart.ts"

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/src/UserPromptSubmit.ts"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/src/PostToolUse.ts"

• Stop

  "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/src/UpdateContext.ts"

• SessionEnd

  "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/src/EvaluateSession.ts"

• SessionEnd

  "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/src/SessionEnd.ts"

• PreCompact

  "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/src/PreCompact.ts"

Similar plugins