compress
Compress a memory/context file into terse form. Saves ~40-50% tokens per session. Usage: /compress <filepath>
IJFW command index. Groups commands by intent: Build / Remember / Ship / Review / Configure.
$ npx -y skills add FerroxLabs/ijfw --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/ijfwContext preview
What this command does when you run it.
IJFW command index. Groups commands by intent: Build / Remember / Ship / Review / Configure.
description: "IJFW command index. Groups commands by intent: Build / Remember / Ship / Review / Configure."
Single landing surface for IJFW commands, grouped by what the user is trying to do. Print when invoked without arguments.
IJFW -- one interface, 15 platforms, persistent memory across all of them. Build -- plan -- explore /workflow -- quick or deep project workflow (brainstorm -> plan -> build) /team -- set up project-specific agent team during Discovery /consolidate -- compress a memory/context file into terse form Remember -- recall -- audit /handoff -- write a structured session handoff /memory-audit -- list auto-extracted memory entries for review /status -- current mode, memory state, active skills Ship -- commit -- review /ijfw-commit -- terse conventional commit /ijfw-review -- one-line code review comments /cross-audit -- Trident peer review: one OpenAI + one Google + specialist swarm Configure -- mode -- help /mode smart|fast|deep|manual|brutal -- switch IJFW mode /compress -- compress context files /metrics -- session metrics (tokens, cost, routing) /doctor -- health check (MCP, hooks, memory, caps) /ijfw -- this index
Sub-commands (e.g. `/memory-audit`) route to dedicated command files in this plugin. The `/ijfw` index itself is a no-op that just prints what's available -- no configuration changes.
Natural-language discovery: also list by intent in chat if user asks "what can IJFW do" / "list commands" / "what's available".
IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.
Repo: FerroxLabs/ijfw
Compress a memory/context file into terse form. Saves ~40-50% tokens per session. Usage: /compress <filepath>
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
Second-model review. Picks an auditor (codex/gemini/opencode/aider/copilot), excludes the caller, writes a prompt to paste, reads the response back. Usage:…
Adversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux). Counter-args ranked by rebuttal survival…
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage:…
Run IJFW health check (files, MCP server, hooks, memory, caps, framing)