compact-min

compact-min is a command for coding agents from ruizrica/toolkit. It costs 12 tokens per session (422 once invoked), scanned A, original, MIT.

A command that saves a very small summary of the current coding session in a JSON file.

In plain words
What is it for?
Use it to record the original request, current task, recently used files, and detailed continuation instructions in `.context/session-state.json`.
Why use it?
It gives a fresh agent the essential context needed to continue after the session is cleared, without saving broader memory.

Command

Part of the toolkit plugin — 1 skill, 2 commands, 5 agents 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 commands/ruizrica/toolkit/compact-min
Clone the repo
git clone --depth 1 https://github.com/ruizrica/toolkit

Or install toolkit, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 5 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 compact-min

README.md
[![agentmods](https://agentmods.dev/badge/commands/ruizrica/toolkit/compact-min.svg)](https://agentmods.dev/commands/ruizrica/toolkit/compact-min)
Your own site
<a href="https://agentmods.dev/commands/ruizrica/toolkit/compact-min"><img src="https://agentmods.dev/badge/commands/ruizrica/toolkit/compact-min.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 422 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 $0.00012 $0.00422
Opus 5 $0.00006 $0.00211
Sonnet 5 $0.00002 $0.00084
Haiku 4.5 $0.00001 $0.00042

Measured 4d ago against content hash 6249905c1e78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compact-min 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 4d 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.

plugins/toolkit/commands/compact-min.md · 54 lines

What it actually says

Ultra-Minimal Session Compact

Generate a minimal session snapshot for fast context restoration.

Instructions

  1. Introspect the conversation to extract:

    • original_request: What the user originally asked for (1 sentence)
    • current_task: What you're actively working on right now (1 sentence)
    • key_files: Array of absolute file paths recently read/edited (max 5)
    • continuation_prompt: A detailed prompt that tells a fresh agent exactly how to continue (2-3 sentences, be specific about next steps)
  2. Write a single JSON file to .context/session-state.json: IMPORTANT: You must use the EXACT file path .context/session-state.json. Do not save it anywhere else or use quotes around the path unless required by the shell.

{
  "timestamp": "[ISO timestamp]",
  "original_request": "[what user asked]",
  "current_task": "[what you're doing now]",
  "key_files": ["[file1]", "[file2]"],
  "continuation_prompt": "[Detailed instructions for continuing. Include: what's done, what's next, any blockers or gotchas discovered.]"
}
  1. Report completion with the restore command.

Quality Bar for continuation_prompt

The continuation_prompt is the most important field. It should enable a fresh agent to:

  • Understand the goal immediately
  • Know exactly what step to take next
  • Avoid repeating completed work
  • Be aware of any pitfalls discovered

Example good prompt: "User wants a REST API for todo items. Created GET /todos endpoint, tested working. Next: implement POST /todos with validation. Note: the db connection pool maxes at 10, discovered this causes timeouts under load."

Example bad prompt: "Working on API stuff."

Output

After writing, say:

Session compacted to .plans/session-state.json

To restore after /clear:
/restore
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. 4d ago First seen · 54 lines · 12 tokens per session scan A 6249905c1e78

Subscribe to this mod's changes

compact-min is a command published in the GitHub repository ruizrica/toolkit (5 stars, last pushed 19d ago), licensed MIT. It adds 12 tokens to every session and 422 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.