lean-compress

A command that condenses a memory file, such as CLAUDE.md or notes, while preserving its technical details. A memory file gives a coding agent instructions and project context in later sessions.

In plain words
What is it for?
Use it to compress agent instructions or project notes, preserve commands and paths, verify the result, and restore the original if important content was lost.
Why use it?
Shorter memory costs fewer input tokens each session, while the original is backed up and the rewritten file is checked for lost technical information.

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/ousid/lean/lean-compress
Clone the repo
git clone --depth 1 https://github.com/ousid/lean
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 329 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 $0.00018 $0.00329
Opus 5 $0.00009 $0.00164
Sonnet 5 $0.00004 $0.00066
Haiku 4.5 $0.00002 $0.00033

Measured yesterday against content hash 1840fe0ac68d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lean-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 yesterday.

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.

commands/lean-compress.md · 19 lines

What it actually says

Compress the memory file at "$ARGUMENTS" into a denser form that costs fewer input tokens on every future session, without losing any meaning.

Steps:

  1. First back up the original: copy "$ARGUMENTS" to "$ARGUMENTS.bak".
  2. Rewrite "$ARGUMENTS" in place, following these rules:
    • Preserve byte for byte: every code block, inline code span, command, file path, URL, config key and value, and env var name. Never reword or reformat these.
    • Compress only the prose around them. Drop filler, merge redundant lines, use terse fragments, remove restated context.
    • Keep every distinct instruction, rule, fact, and preference. This is about cutting words, not information. If in doubt, keep it.
    • Keep Laravel and PHP terms verbatim (Eloquent, Artisan, Blade, facades, php artisan).
  3. Verify nothing technical was lost, and show me the output: node "${CLAUDE_PLUGIN_ROOT}/bin/lean-compress.mjs" check "$ARGUMENTS.bak" "$ARGUMENTS"
  4. If the verifier prints PRESERVATION: FAIL, restore from the .bak file and tell me exactly which item was lost. Do not keep a rewrite that failed the check.
  5. If it passes, report the size reduction from the verifier and remind me the original is saved at "$ARGUMENTS.bak".
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. yesterday First seen · 19 lines · 18 tokens per session scan A 1840fe0ac68d

Subscribe to this mod's changes

lean-compress is a command published in the GitHub repository ousid/lean (4 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 329 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.