lcm-curate

lcm-curate is a command for Claude Code from lossless-claude/lcm. It costs 20 tokens per session (371 once invoked), scanned A, original, MIT.

A command that runs a memory-curation pipeline: importing, compacting, and promoting stored project memories. It can process the current project or all projects and supports a dry-run preview.

In plain words
What is it for?
Use it to curate project memory, process every project, or preview the changes with --dry-run before writing anything.
Why use it?
It combines the repeated memory-maintenance steps in the required order, with verbose output by default.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the lcm plugin — 8 skills, 10 commands, 4 agents shipped together

Good fit Use it to curate project memory, process every project, or preview the changes with --dry-run before writing anything.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add lossless-claude/lcm
Claude Code
/plugin install lcm

Made for: Claude Code.

Or install lcm, the plugin that ships this one along with the rest of its 8 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-curate

README.md
[![agentmods](https://agentmods.dev/badge/commands/lossless-claude/lcm/lcm-curate.svg)](https://agentmods.dev/commands/lossless-claude/lcm/lcm-curate)
Your own site
<a href="https://agentmods.dev/commands/lossless-claude/lcm/lcm-curate"><img src="https://agentmods.dev/badge/commands/lossless-claude/lcm/lcm-curate.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 371 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.
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 $0.00020 $0.00371
Opus 5 $0.00010 $0.00186
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 8d ago against content hash 7deb34fa3a9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lcm-curate 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.

.claude-plugin/commands/lcm-curate.md · 40 lines

What it actually says

/lcm-curate

Run the full memory curation pipeline: import, compact, and promote.

Instructions

Run the following commands sequentially via Bash. Always use --verbose on import and promote by default:

lcm import --verbose && lcm compact && lcm promote --verbose

If lcm is not on PATH (marketplace install), use the plugin-relative binary instead:

node "${CLAUDE_PLUGIN_ROOT}/lcm.mjs" import --verbose && node "${CLAUDE_PLUGIN_ROOT}/lcm.mjs" compact && node "${CLAUDE_PLUGIN_ROOT}/lcm.mjs" promote --verbose

Options

Pass user-specified flags through to the commands that support them:

  • --all — Process all projects (default: current project only); applies to all three commands
  • --no-verbose — Suppress verbose output (verbose is on by default)
  • --dry-run — Preview without writing; applies to all three commands

For example:

  • /lcm-curate --alllcm import --all --verbose && lcm compact --all && lcm promote --all --verbose
  • /lcm-curate --dry-runlcm import --dry-run --verbose && lcm compact --dry-run && lcm promote --dry-run --verbose
  • /lcm-curate --no-verboselcm import && lcm compact && lcm promote

The pipeline stops on the first failure and reports the result.

Display the output verbatim.

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 · 40 lines · 20 tokens per session scan A 7deb34fa3a9b

Subscribe to this mod's changes

lcm-curate is a command published in the GitHub repository lossless-claude/lcm (24 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 371 once invoked, about $0.0001 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.