lcm: Skill for Claude Code

.agents/skills/lcm-context/SKILL.md

lcm-context is a skill for Claude Code, Codex from lossless-claude/lcm. It costs 41 tokens per session (1,057 once invoked), scanned A, original, MIT.

Instructions for using lcm, a command-line memory system that stores project decisions and past context in a searchable SQLite database. It is intended for recalling information before work and saving decisions afterward.

In plain words
What is it for?
Use it to search prior architecture or implementation decisions, find exact past discussion, and store new findings or decisions after making changes.
Why use it?
It helps an agent recover project context across sessions instead of relying only on the current conversation.

Skill for Claude CodeCodex

Written for Claude Code: SessionEnd hook event. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is lossless-claude/lcm's own configuration. It tells Claude Code and Codex how to work on lcm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lcm configures →

Part of the lcm plugin — 7 skills, 10 commands, 4 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to lossless-claude/lcm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lossless-claude/lcm/main/.agents/skills/lcm-context/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lossless-claude/lcm

Made for: Claude Code, Codex.

Or install lcm, the plugin that ships this one along with the rest of its 7 skills, 10 commands, 4 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lcm-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/lossless-claude/lcm/lcm-context.svg)](https://agentmods.dev/skills/lossless-claude/lcm/lcm-context)
Your own site
<a href="https://agentmods.dev/skills/lossless-claude/lcm/lcm-context"><img src="https://agentmods.dev/badge/skills/lossless-claude/lcm/lcm-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01057
Opus 5 $0.00020 $0.00528
Sonnet 5 $0.00008 $0.00211
Haiku 4.5 $0.00004 $0.00106

Measured 8d ago against content hash ee27f50d1dc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lcm-context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/lcm-context/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lcm Memory — Universal Agent Guide

Use the lcm CLI to retrieve and store project memory across sessions. Install: npm install -g @lossless-claude/lcm

Memory is stored in SQLite (FTS5) and accessed via CLI commands or MCP tools.

Workflow

  1. Before Thinking: Run lcm search or lcm grep to recall past decisions and context.
  2. After Implementing: Run lcm store to persist new decisions, patterns, or findings.

Commands

1. Search Memory (broad recall)

Retrieve relevant context across all past sessions using full-text search.

Use when:

  • You need to recall past decisions, patterns, or architectural context
  • Before performing any action, to check for relevant rules or preferences
  • Your context does not contain information you need

Do NOT use when:

  • The information is already present in your current context
  • The query is about general knowledge, not project memory
lcm search "how was auth implemented"
lcm search "compaction architecture" --tags decision,architecture
lcm search "JWT token" --layers episodic

2. Grep Memory (exact match)

Search raw conversation transcripts by keyword or regex.

Use when:

  • You need an exact keyword, error message, or function name from past sessions
  • Search returned too many broad results and you need to narrow down

Do NOT use when:

  • You need conceptual recall (use lcm search instead)
lcm grep "socket.unref"
lcm grep "JWT" --scope summaries
lcm grep "ECONNREFUSED" --since 2026-03-20

3. Expand a Summary Node

Decompress a summary node from the DAG into its full source content.

Use when:

  • A search or grep result references a summary nodeId and you need more detail
  • Check with lcm describe <nodeId> first to see if it's worth expanding (saves tokens)
lcm describe <nodeId>    # check metadata first
lcm expand <nodeId>      # decompress if relevant
lcm expand <nodeId> --depth 2   # deeper traversal

4. Store a Decision or Finding

Read the full file on GitHub · 136 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 136 lines · 41 tokens per session scan A ee27f50d1dc7

Subscribe to this mod's changes

lcm-context is a skill published in the GitHub repository lossless-claude/lcm (24 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,057 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens