compress

A command that shortens a memory or context file while preserving its actionable instructions. It saves the original file as a backup and reports the token reduction.

In plain words
What is it for?
Use it on a specified memory file when a session needs more usable context. It rewrites prose in a terse form and checks that the instructions remain usable.
Why use it?
Long context files use more of an agent’s available reading space. Compressing them keeps the important commands, paths, dates, headings, and instructions while removing filler.

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/ferroxlabs/ijfw/compress
Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ijfw
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 123 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 $0.00028 $0.00123
Opus 5 $0.00014 $0.00062
Sonnet 5 $0.00006 $0.00025
Haiku 4.5 $0.00003 $0.00012

Measured 3d ago against content hash 1318814d31f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

claude/commands/compress.md · 13 lines

What it actually says

Compress the specified file using ijfw-compress skill rules.

  1. Back up original as .original.md
  2. Rewrite prose in compressed form: drop articles, filler, hedging. Fragments OK.
  3. Preserve exactly: code blocks, URLs, file paths, commands, headings, dates, versions.
  4. Validate the compressed version retains all actionable instructions.
  5. Report: original tokens → compressed tokens (% saved).
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. 3d ago First seen · 13 lines · 28 tokens per session scan A 1318814d31f2

Subscribe to this mod's changes

compress is a command published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 9d ago), licensed MIT. It adds 28 tokens to every session and 123 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 2026-08-30.