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.
npx agentmods add commands/ruizrica/toolkit/compact-mingit clone --depth 1 https://github.com/ruizrica/toolkitWrote 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.
[](https://agentmods.dev/commands/ruizrica/toolkit/compact-min)<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>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.
| Model | Per session | Once 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 |
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.
What it actually says
Ultra-Minimal Session Compact
Generate a minimal session snapshot for fast context restoration.
Instructions
-
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)
-
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.]"
}
- 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
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.
- 4d ago First seen · 54 lines · 12 tokens per session scan A 6249905c1e78
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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
neo-review
Get Neo's code review with semantic matching against past findings in memory. Use on a diff or module before merge, especially where earlier mistakes in this codebase are likely to recur. Skip for formatting, lint-catchable issues, and single-line changes.