ijfw-agents-md
Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent…
@ferroxlabsInstall SkillDevelopment
Skill
/ijfw-compress
Compress memory/context files into terse form. Trigger: /compress, compress file
Claude Code
$ npx -y skills add FerroxLabs/ijfw --skill ijfw-compress --agent claude-code
Codex
$ npx skills add FerroxLabs/ijfw --skill ijfw-compress -a codex -y
Cursor
$ npx skills add FerroxLabs/ijfw --skill ijfw-compress -a cursor -y
Gemini CLI
$ npx skills add FerroxLabs/ijfw --skill ijfw-compress -a gemini-cli -y
GitHub Copilot
$ npx skills add FerroxLabs/ijfw --skill ijfw-compress -a github-copilot -y
OpenCode
$ npx skills add FerroxLabs/ijfw --skill ijfw-compress -a opencode -y
Windsurf
$ npx skills add FerroxLabs/ijfw --skill ijfw-compress -a windsurf -y
SKILL.md
ijfw-compress.SKILL.mdname: ijfw-compress description: "Compress memory/context files into terse form. Trigger: /compress, compress file"
Compress the target file. Preserve all meaning. Reduce tokens.
Rules:
- Drop: articles (a/an/the), filler (just/really/basically), hedging, pleasantries.
- Fragments OK. Short synonyms (big not extensive, fix not implement a solution).
- Arrows for causality (X → Y).
- Abbreviate common terms (DB/auth/config/req/res/fn/impl/env/deps).
- Preserve EXACTLY: code blocks, URLs, file paths, commands, headings, dates, versions, technical terms.
- Only compress prose. Never touch code.
Process: 1. Back up: cp <file> <file>.original.md 2. Compress prose sections. 3. Validate: all headings preserved, all code blocks intact, all URLs unchanged. 4. Report savings as measured per-artifact: "Compressed: <before> -> <after> tokens (<percent>% saved on this artifact)". Report the MEASURED number from wc -w / token-count on the actual files. Do NOT claim a fixed percentage — savings vary widely by input shape (verbose handoffs compress further than dense memory files). v1.5.0 audit removed the legacy hardcoded "50% / 40-50%" framing from this skill in favor of measured-per-receipt reporting.
Stats
215
Stars
44
Forks
Active
Maintenance
JavaScript
Language
MIT
License
Last commit
Created
Ships withijfw
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.
21436 skills37 agents1 MCP
Stars on GitHub
Momentum
- stars in total
- 214
Other skills on ijfw.
@ferroxlabsInstall Skillijfw-auto-memorize
Session-end auto-extraction of lessons, errors, fixes, and user feedback into structured memory. Fires at session end. Requires…
@ferroxlabsInstall Skillijfw-commit
Terse conventional commits. Trigger: commit, git commit, /ijfw-commit
@ferroxlabsInstall Skillijfw-complete-mileston…
Use when a milestone is shipping and you need to archive its artifacts, generate a summary, and seed the next milestone. Trigger:…
@ferroxlabsInstall Skillijfw-compute
Use when the user says: 'compute', 'crunch this', 'analyze logs', 'aggregate the data', 'run a script', 'dedupe', 'count by',…
@ferroxlabsInstall Skillijfw-core
IJFW efficiency layer -- smart output, routing, context discipline. Always active. Trigger: any IJFW interaction. Disable: 'ijfw…
@ferroxlabsInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about ijfw-compress.
- Which coding agents can use ijfw-compress?
- ijfw-compress installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.