ltm:compact

ltm:compact is a skill for Claude Code from LaserPhaser/claude-ltm. It costs 17 tokens per session (485 once invoked), scanned A, original, MIT.

A session review that records important technical decisions in a project's .memory/DECISIONS.md file. It can also update project status and link to longer decision notes.

In plain words
What is it for?
Capturing architecture choices, library selections, business rules, blockers, and changes made during a coding session.
Why use it?
It prevents decisions, rejected approaches, constraints, and open questions from being lost when work is handed to another developer.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-ltm plugin — 3 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/laserphaser/claude-ltm/ltm-compact
Any agent
npx skills add LaserPhaser/claude-ltm --skill ltm-compact
Clone the repo
git clone --depth 1 https://github.com/LaserPhaser/claude-ltm

Made for: Claude Code.

Or install claude-ltm, the plugin that ships this one along with the rest of its 3 skills.

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 ltm:compact

README.md
[![agentmods](https://agentmods.dev/badge/skills/laserphaser/claude-ltm/ltm-compact.svg)](https://agentmods.dev/skills/laserphaser/claude-ltm/ltm-compact)
Your own site
<a href="https://agentmods.dev/skills/laserphaser/claude-ltm/ltm-compact"><img src="https://agentmods.dev/badge/skills/laserphaser/claude-ltm/ltm-compact.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 485 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00485
Opus 5 $0.00009 $0.00243
Sonnet 5 $0.00003 $0.00097
Haiku 4.5 $0.00002 $0.00049

Measured 5d ago against content hash 12bfbecb62b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ltm:compact 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 5d 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.

skills/ltm-compact/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compact — Extract Decisions to Memory

Perform a compact pass: review everything that happened in this session and capture any significant decisions that aren't yet in .memory/DECISIONS.md.

What to do

  1. Read .memory/DECISIONS.md to understand what's already recorded.

  2. Review this session's work. Look for:

    • Architecture or design choices that were made
    • Technology or library selections
    • Approaches that were tried and rejected
    • Business logic decisions or constraints discovered
    • Changes to previously recorded decisions
    • Current project status (focus, blockers, open questions)
  3. For each unrecorded decision:

    • "Significant" = something a teammate joining next week would need to know.
    • Add a ### heading with today's date and up to ~10 lines of context.
    • If the decision is truly complex (>10 lines needed), create a detail file in .memory/details/YYYY-MM-DD-<topic>.md and link to it.
    • If a prior decision was superseded, update it in-place with what changed and why. Add a Changelog entry.
    • Check for duplicates — update existing entries rather than adding new ones.
  4. Update the ## Status section with current focus, blockers, and open questions.

  5. Update the > Auto-maintained by claude-ltm. Last updated: date.

  6. Report to the user what was captured (or that nothing new was found).

Detail file format

When creating a detail file in .memory/details/, use this structure:

---
decision: <title>
date: YYYY-MM-DD
status: ACTIVE
---

<!-- Valid status values: ACTIVE, SUPERSEDED -->

## Context
[Why this decision was needed — 2-3 sentences]

## Decision
[What was chosen and why — concise]

## Alternatives Considered
- Option B: [why rejected]

## Impact
- [Key consequence 1]

Guidelines

  • Keep entries concise. This is a decision log, not documentation.
  • Routine code changes are NOT decisions. Choosing a database IS.
  • When in doubt about significance, record it — pruning is easier than recreating.

Read the full file on GitHub · 69 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. 5d ago First seen · 69 lines · 17 tokens per session scan A 12bfbecb62b2

Subscribe to this mod's changes

ltm:compact is a skill published in the GitHub repository LaserPhaser/claude-ltm (4 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 485 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 2026-08-31.

Related

Other skills, from other repositories

memory-map

Two-tier project memory system. Maintains a global Claude memory snapshot of all ongoing projects AND a per-project STATUS.md file in each project folder that captures last-session state, next actions, blockers, and key locations — so context survives long absences. Operates in two modes. WRITE mode triggers when the…

shandar/memory-map · 215 tokens

memory-prune

Clean stale, outdated, or redundant entries from Claude's stored memory. Use this skill when the user says things like "clean up memory", "prune memory", "memory is getting cluttered", "remove old entries", "consolidate memory", or "trim the memory map". Also trigger proactively when memory approaches its limits — 30…

shandar/memory-map · 147 tokens

memory-recall

Load and summarise stored project memory at the start of a session, or whenever the user asks what Claude remembers about their work. Use this skill when the user says things like "what do you remember", "what's the context", "where did we leave off", "catch me up", "what's the current state", "show me the memory…

shandar/memory-map · 156 tokens

gather-context

Before working on a task, pull the relevant slices of the project's ground truth from the manifest, write a short context brief, and confirm it with the human in one batch. Re-run at each phase boundary, not just at the start.

t1djani/servo · 52 tokens

mem0-dream

Consolidates stored memories by merging duplicates, resolving contradictions, and pruning stale entries. Use when memory count is high, search results feel noisy or repetitive, or periodic cleanup is needed to maintain memory quality.

mem0ai/mem0 · 46 tokens

mem0-tour

Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.

mem0ai/mem0 · 47 tokens