lcm-context
01Skill Claude CodeCodex
You MUST use this before any work to recall project memory, and after implementing to store decisions. Lossless-claude (lcm) provides persistent cross-session memory via CLI commands.
Skill Claude CodeCodex
You MUST use this before any work to recall project memory, and after implementing to store decisions. Lossless-claude (lcm) provides persistent cross-session memory via CLI commands.
Skill Claude CodeCodex
Use when the user says 'cut a release', 'release vX.Y.Z', 'publish a new version', or 'bump the version'. Covers the full release flow: version bump → PR to main → CI → merge → publish → develop sync.
Command Claude Code
Compact conversation messages into DAG summary nodes.
Command Claude Code
Run the full memory curation pipeline: import, compact, and promote.
Command Claude Code
Scan recent Claude Code session transcripts for hook failures, MCP disconnects, and stale lcm hook setup.
Command Claude Code
Run lossless-claude diagnostics — checks daemon, hooks, MCP server, and summarizer health.
Command Claude Code
Run the lcm self-test suite — validates all CLI commands, hooks, MCP tools, and resilience across 39 checks in 10 phases.
Command Claude Code
Import Claude Code session transcripts into lcm memory.
Command Claude Code
Promote durable insights from summaries into cross-session memory.
Command Claude Code
Manage sensitive patterns for lossless-claude secret redaction — list, add, remove, test, or purge patterns.
Command Claude Code
Show lossless-claude memory inventory, compression ratios, and DAG statistics.
Command Claude Code
Show daemon state and project memory statistics.
Plugin Claude Code
Plugin marketplace listing 1 plugin: lcm.
Plugin Claude Code
Lossless context management — DAG-based summarization that preserves every message.
Skill Claude CodeCodex
This skill should be used when the user asks to "run lcm dogfood", "self-test lcm", "validate lcm build", "test lcm hooks", "check lcm mcp tools", or mentions lcm QA, regression testing, or pre-release validation. Runs a comprehensive 39-check self-test across all CLI commands, hooks, MCP tools, and resilience.
Skill Claude CodeCodex
Run the E2E validation checklist against a real lcm installation. Tests daemon, hooks, import, compact, promote, retrieval, and resilience. Pass a flow name for a subset (import, compact, promote, curate, retrieval, hooks, doctor, cleanup), or omit for the full suite.
Skill Claude CodeCodex
Rebuild, reinstall, and restart lossless-claude from source. Fixes hooks, restarts daemon, runs diagnostics. Trigger: /lossless-claude:upgrade.
Skill Claude CodeCodex
Lossless context management — search and store persistent memory across sessions.
Instructions file GitHub Copilot
Instructions for lossless-claude/lcm, covering copilot review instructions — lossless-claude (lcm), primary concerns, database connection pattern (highest priority), pragma enforcement and type safety.
Instructions file GitHub Copilot
Instructions for lossless-claude/lcm, a project described as: Lossless context management for Claude Code.
Instructions file CodexOpenCode
Instructions for lossless-claude/lcm, covering repository instructions, pr review and merge, local environment stability, documentation requirements and coding style.
Instructions file
Instructions for lossless-claude/lcm: These override the superpowers default paths (docs/superpowers/specs/ and docs/superpowers/plans/).
Agent
Use this agent to review compaction quality — checks whether summaries accurately preserve important information from source messages. Use proactively after compaction completes, or when the user asks about summary quality. Examples.
Agent
Use this agent for deep investigation of lossless-claude health issues — goes beyond the doctor checklist to find root causes. Examples.