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.
git clone --depth 1 https://github.com/Achitokun14/claude-universalWrote 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/achitokun14/claude-universal/compress)<a href="https://agentmods.dev/commands/achitokun14/claude-universal/compress"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/compress/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/achitokun14/claude-universal/compress"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/compress.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00016 | $0.00413 |
| Opus 5.5 | $0.00006 | $0.00165 |
| Sonnet 5.5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
compress scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Produce a handoff document that captures the essential state of THIS conversation so a future session can pick up without context.
Steps:
-
Review the conversation and extract:
- Goal: what the user is ultimately trying to accomplish
- Decisions made: concrete choices, not considerations
- Files touched: list with 1-line reason each
- Open threads: unfinished tasks, unresolved questions, blockers
- Next step: the single most useful thing to do next
- Gotchas: anything a future session should be warned about (bugs found, dead ends, misleading signals)
-
Write to
~/Desktop/ACTIVITIES/llm-wiki/handoffs/$(date +%Y%m%d-%H%M)-<slug>.md:# Handoff: <short title> **Date:** YYYY-MM-DD HH:MM **Session duration:** approximate **Project / cwd:** <path> ## Goal <1-2 sentences> ## Decisions - ... ## Files touched | file | change | |------|--------| | path | reason | ## Open threads - [ ] ... ## Next step <one concrete action> ## Gotchas - ... -
Also append a pointer line to
~/Desktop/ACTIVITIES/llm-wiki/$(date +%Y-%m-%d).md:- 🗂️ Handoff saved: [<title>](handoffs/YYYYMMDD-HHMM-slug.md) -
Print the absolute path of the handoff file to chat so the user can paste it into a new session.
Keep the handoff under 200 lines. Omit anything that can be re-derived from reading the code.
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.
- 2mo ago First seen · 52 lines · 16 tokens per session scan A 9faf8a0a9c8e
compress is a command published in the GitHub repository Achitokun14/claude-universal (2 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 413 once invoked, about $0.0001 per session on Opus 5.5. 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.
compress compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compressAchitokun14/claude-universal | Command | 2 | 4mo ago | MIT | A | 16 | Claude Code |
| forgetskynetcmd/m3-memory | Command | 30 | today | Apache-2.0 | A | 13 | Claude Code |
| recallnaimkatiman/continuous-improvement | Command | 9 | 6d ago | MIT | A | 44 | Claude Code |
| graphskynetcmd/m3-memory | Command | 30 | today | Apache-2.0 | A | 20 | Claude Code |
| getskynetcmd/m3-memory | Command | 30 | today | Apache-2.0 | A | 11 | Claude Code |
| memory-reviewstefan-jansen/claude-code-toolkit | Command | 93 | 4mo ago | MIT | A | 14 | Claude Code |
| indexstefan-jansen/claude-code-toolkit | Command | 93 | 4mo ago | MIT | A | 8 | Claude Code |