compact

A command that summarizes a coding session, records a daily log, optionally updates project memory, and saves restore instructions before clearing the conversation.

In plain words
What is it for?
Use it at the end of a work session to save state in `.context/session-state.json`, append a dated log, and get instructions for continuing later.
Why use it?
It prevents important decisions, files, and unfinished work from being lost when a session ends.

Command

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 commands/ruizrica/toolkit/compact
Clone the repo
git clone --depth 1 https://github.com/ruizrica/toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 683 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 $0.00000 $0.00683
Opus 5 $0.00000 $0.00342
Sonnet 5 $0.00000 $0.00137
Haiku 4.5 $0.00000 $0.00068

Measured 2d ago against content hash 4805436a286d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

docs/commands/compact.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/compact

Memory-aware session compact. Saves your current session state, writes a daily log entry, and optionally updates MEMORY.md before using /clear.

Usage

/compact

Arguments

This command takes no arguments. It introspects the current conversation to extract relevant state.

How It Works

  1. Introspect - Analyze the conversation to extract summary, key decisions, files, continuation prompt, and any stable facts
  2. Daily Log - Append a formatted entry to ~/.claude/agent-memory/daily-logs/YYYY-MM-DD.md
  3. MEMORY.md - If stable facts were discovered, update the project's MEMORY.md (optional)
  4. Session State - Write .context/session-state.json (V2 schema)
  5. Report - Confirm completion and provide restore instructions

Daily Log Format

Each /compact appends an entry like:

## 14:30 - my-project
**Summary:** Implemented OAuth flow and wrote unit tests for token refresh
**Key decisions:**
- Chose RS256 over HS256 for JWT signing
- Used middleware pattern for auth checks
**Files:** /src/auth/oauth.ts, /src/auth/tokens.ts, /tests/auth/oauth.test.ts
**Continue:** Run the failing test for JWT expiry validation and fix the UTC edge case
---

Session State Format (V2)

{
  "$schema": "session-state-v2",
  "project": "my-project",
  "cwd": "/path/to/project",
  "ts": "2026-01-30T14:30:00Z",
  "continue": "Run the failing test for JWT expiry...",
  "task": "Implement token refresh with RS256",
  "todos": [{"t": "Fix UTC edge case", "done": false}],
  "files": ["/src/auth/oauth.ts"],
  "files_read": ["/src/config.ts"]
}

Output Locations

File Purpose
~/.claude/agent-memory/daily-logs/YYYY-MM-DD.md Daily log entry
.context/session-state.json Session state for /restore
~/.claude/projects/{key}/memory/MEMORY.md Stable facts (if updated)

When to Use

Read the full file on GitHub · 100 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. 2d ago First seen · 100 lines · 0 tokens per session scan A 4805436a286d

Subscribe to this mod's changes

compact is a command published in the GitHub repository ruizrica/toolkit (5 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 683 tokens. 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.