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

Session Compression

ASecurity

Lossless session context compression for token efficiency. Extracts entities, decisions, and state into compact format before context window fills. 10-30x reduction in context size while preserving all actionable information.

530 stars
0 votes
0 copies
1 views
Added 5/29/2026
ai-agentstypescriptgosqlnextjsexpressdebuggingapidatabase

Works with

api

Security Analysis

A100/100

Scanned 5/29/2026

$npx -y skills add vibeeval/vibecosystem --skill session-compression --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Session Compression?

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

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

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: session-compression
description: "Lossless session context compression for token efficiency. Extracts entities, decisions, and state into compact format before context window fills. 10-30x reduction in context size while preserving all actionable information."
---

# Session Compression

Compress session context without losing actionable information. Use before context window fills up or when handing off between sessions.

## Why Compress

| Metric | Raw Context | Compressed |
|--------|------------|------------|
| Token count | ~50K | ~3-5K |
| Decision count | Scattered | Indexed |
| File references | Buried in prose | Listed |
| Error history | Verbose stack traces | Root cause + fix |
| Reduction | 1x | 10-30x |

## Compression Format

### ACDE Format (Actions, Context, Decisions, Entities)

```markdown
## A: Actions Completed
- [x] Refactored auth middleware (auth.ts, middleware.ts)
- [x] Added rate limiting (api/limiter.ts)
- [ ] Pending: Write tests for rate limiter

## C: Context
- Project: my-app (Next.js 16, TypeScript)
- Branch: feat/auth-refactor (3 commits ahead of main)
- Blockers: None

## D: Decisions
- D1: JWT over sessions (stateless, mobile-friendly)
- D2: 100 req/min rate limit (based on load test)
- D3: Rejected Redis session store (overkill for current scale)

## E: Entities
- Files: auth.ts:42, middleware.ts:15, api/limiter.ts (new)
- Deps: jsonwebtoken@9.0.0, express-rate-limit@7.0.0
- APIs: POST /auth/login, POST /auth/refresh, GET /auth/me
```

## When to Compress

1. **Pre-compact**: Before context window compression (auto via hook)
2. **Session handoff**: When switching between sessions on same project
3. **Agent delegation**: When handing complex task to another agent
4. **Milestone reached**: After completing a significant piece of work

## Compression Rules

### What to Keep (Lossless)
- All decisions with reasoning (D1, D2, D3...)
- File paths and line numbers of changes
- Unresolved blockers or pending items
- Error root causes (not full stack traces)
- External constraints

### What to Drop (Safe)
- Exploratory reads that didn't lead anywhere
- Redundant confirmations ("yes that looks good")
- Intermediate debugging steps (keep only root cause)
- Tool output that was just for verification
- Repeated context that's already in CLAUDE.md

### Entity Coding
Replace verbose references with short codes:

```
"the authentication middleware in src/middleware/auth.ts" -> "auth.ts"
"the user requested that we use JWT tokens" -> "D1: JWT"
"the PostgreSQL database running on port 5432" -> "pg:5432"
```

## Integration

### Pre-Compact Hook
The `session-compressor` hook automatically generates ACDE format before context compression:

1. Scans recent tool calls for file paths -> E section
2. Extracts decisions from conversation -> D section
3. Lists completed/pending tasks -> A section
4. Summarizes project state -> C section

### With Memory Palace
Compressed sessions feed into the palace:
- Decisions -> stored as drawers in appropriate rooms
- Entities -> indexed for cross-session search
- Actions -> tracked in thoughts/PROGRESS.md

### With Compass Agent
Compass uses ACDE format for "where were we?" recovery:
```
Last session compressed:
A: 3 done, 1 pending (rate limiter tests)
D: JWT auth, 100rpm limit
E: auth.ts, middleware.ts, limiter.ts
```

Attribution

vibeevalvibeeval
View sourceSee grades on GitHubMore from vibeeval →
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', ...

698621 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 →