Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Compact Session

ASecurity

Use when asked to manually compact a session's memory, trigger session summarization, or reduce a long session's context footprint.

6 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsgobashnodedatabase

Works with

cli

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add BrennonTWilliams/little-loops --skill compact-session --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Compact Session?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Compact Session
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brennontwilliams-compact-session/badge)](https://www.skillsdirectory.com/skills/brennontwilliams-compact-session)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: compact-session
description: Use when asked to manually compact a session's memory, trigger session summarization, or reduce a long session's context footprint.
disable-model-invocation: true
allowed-tools:
  - Bash(ll-compact-session:*)
  - Read
metadata:
  short-description: Use when asked to manually compact a session's memory or trigger session summ
---

# Compact Session Skill

Manually triggers session-memory compaction for one session — the same LCM
compaction path (`session_store.compact_session`) that fires automatically in
the background once a session crosses the soft token threshold (FEAT-2598).
Produces leaf/condensed `summary_nodes` rows and prints the resulting
`CompactResult` (summary text, covered message count, token estimate).

This is the LCM/semantic-summarization axis — distinct from `ll-session
compact`, which sweeps the separate *retention* axis (`kind='retention'`
`raw_events` summarization, ENH-1906/ENH-2581). Do not confuse the two.

## When to Activate

Proactively offer or invoke this skill when the user:

- Asks to compact, summarize, or condense a session manually
- Wants to reduce a long-running session's context footprint before continuing
- Asks whether a session has been compacted yet, or wants to see its summary
- Mentions the session is approaching a context limit and wants to trigger
  summarization early rather than waiting for the automatic soft-threshold trigger

## Arguments

$ARGUMENTS

- **session_id** (required) — the session to compact. If the user doesn't name
  one, use the current session's ID (available from the host CLI's session
  context) or ask which session they mean.
- `--db PATH` (optional) — session database path (default: `.ll/history.db`)
- `--json` (optional) — machine-readable output

## How to Use

Run the `ll-compact-session` CLI command:

```bash
ll-compact-session SESSION_ID
```

For programmatic access (e.g. from another skill or loop evaluator):

```bash
ll-compact-session SESSION_ID --json
```

The JSON payload includes `new_leaves` (leaf nodes created this run),
`summary_text` (the condensed summary, `null` if the session has fewer than
two leaf blocks), `compacted_messages` (covered `message_events` ids), and
`context_token_estimate`.

Compaction is idempotent — repeated calls do not create duplicate nodes.
Note that `history.compaction.enabled` (default `false` in
`.ll/ll-config.json`) gates whether an LLM summary is produced at all; when
disabled, `ll-compact-session` still runs but the leaf/condensed summaries
fall back to deterministic truncation (no LLM cost) per the existing LCM
three-level escalation in `session_store._summarize_block`.

## Examples

| User says | Action |
|-----------|--------|
| "Compact this session before we keep going" | `ll-compact-session <current-session-id>` |
| "Has session abc123 been summarized?" | `ll-compact-session abc123 --json`, report `summary_text` |
| "This loop's session is getting huge, trigger compaction now" | `ll-compact-session <session-id>` |

Attribution

BrennonTWilliamsBrennonTWilliams
View sourceSee grades on GitHubMore from BrennonTWilliams →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →