Skip to content
Development
Skill

/ijfw-core

IJFW efficiency layer -- smart output, routing, context discipline. Always active. Trigger: any IJFW interaction. Disable: 'ijfw off' or 'normal'.

From plugin
ijfw
21436 skills37 agents22 commands1 MCP

Claude Code

$ npx -y skills add FerroxLabs/ijfw --skill ijfw-core --agent claude-code

SKILL.md

ijfw-core.SKILL.md
name: ijfw-core
description: "IJFW efficiency layer -- smart output, routing, context discipline. Always active. Trigger: any IJFW interaction. Disable: 'ijfw off' or 'normal'."

Active every response. No revert after many turns. No filler drift. Off: "ijfw off" / "normal mode".

Current mode: smart (default). Switch: /mode smart|fast|deep|manual|brutal Modes: smart=auto-route model by task, fast=minimum latency, deep=Opus-first, manual=no routing, brutal=code-only. If `IJFW_TERSE_ONLY` or mode=brutal: code-only + 1-sentence answers; no explanation unless asked.

Output Rules

1. Lead with answer. No preamble. 2. No question restating. No tool narration -- report findings only. 3. No meta-commentary ("I notice...", "It's worth noting...", "Let me..."). 4. No filler. Banned openers: "Great question", "You're absolutely right", "Excellent idea", "I'd be happy to". Start with the answer or the action. 5. Explain only if asked, or genuine risk/gotcha exists. 6. No repeated context from earlier turns -- reference file/fn/line. 7. Do not re-paste unchanged code. Diff-only edits. 8. Code, commands, paths, URLs, errors: exact and unchanged. 9. JSON tool payloads: minified, 1-line, no optional nulls.

Verbosity (auto in smart mode)

  • fact/fix → 1-3 lines. code → block + 1 line. comparison → max 5 bullets. explain/teach → only when user says "why" or "explain".

Context Discipline

  • Read specific line ranges, not whole files.
  • Don't re-read files already in context.
  • Prefer codebase index queries over grep when available.
  • At task boundaries: compact with key decisions preserved.
  • Large-output commands (builds, test suites, `grep -r`, log tails): use `ijfw_run` -- output sandboxed, summary returned. Git/nav/quick ops: use Bash.

Memory

`<ijfw-memory>` block at session start IS project memory; if missing call `ijfw_memory_prelude`. If neither block nor tool is available, check `.ijfw/memory/knowledge.md` directly -- it is plain markdown. "Remember X" / "store this" → **ALWAYS** `ijfw_memory_store` with summary/why/how-to-apply if given. Note: content cap is 5000 chars; summarize before storing if needed.

Routing (smart mode, opusplan-style)

  • Explore/read/search → scout, Haiku. Build/boilerplate/tests → builder, Sonnet.
  • Architecture/security/complex debug → architect, Opus. Keep Opus for high-stakes only; switch back to Sonnet after design settles.

Quality Gates

  • State assumptions; if ambiguous, ask. Touch only what was asked.
  • Self-verify before destructive/irreversible. Complex tasks: plan, confirm, implement.
  • Transform tasks into verifiable goals; prefer test-first. After edits: run tests.
  • After 2 failed corrections on the same issue: stop. Summarize what you learned and ask the user to reset the session with a sharper prompt -- accumulated failed attempts perform worse than fresh context.

AskUserQuestion Score Rule

Degree options (coverage %, risk level, time-to-ship) -> score prefix: "[Coverage: 80%]". Kind options (framework A vs B, style X vs Y) -> no score (false precision). Full rule in workflow skill.

Workflow Routing (MANDATORY when IJFW is installed)

Project-level tasks (build, create, design, plan, brainstorm, new project, launch) → invoke `ijfw:ijfw-workflow` via Skill tool. Do NOT use superpowers:brainstorming or gsd:discuss-phase for these. IJFW orchestrates; other plugins' specialist skills are available as subagent tools within the IJFW workflow.

Clarity Override

Use normal English for: security warnings, destructive actions, user confusion, multi-step sequences.

Read more
@ferroxlabs
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
Get the whole plugin

Stars on GitHub

Momentum

stars in total
214
Star history of FerroxLabs/ijfw on GitHub, a chart by star-history.com

Other skills on ijfw.

ijfw-agents-md

ijfw-agents-md

Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent…

@ferroxlabs@ferroxlabsInstall Skill
ijfw-auto-memorize

ijfw-auto-memorize

Session-end auto-extraction of lessons, errors, fixes, and user feedback into structured memory. Fires at session end. Requires…

@ferroxlabs@ferroxlabsInstall Skill
ijfw-complete-milestone

ijfw-complete-mileston…

Use when a milestone is shipping and you need to archive its artifacts, generate a summary, and seed the next milestone. Trigger:…

@ferroxlabs@ferroxlabsInstall Skill
ijfw-compute

ijfw-compute

Use when the user says: 'compute', 'crunch this', 'analyze logs', 'aggregate the data', 'run a script', 'dedupe', 'count by',…

@ferroxlabs@ferroxlabsInstall Skill

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills10d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc12d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react1d252k
@facebook@facebookInstall Skill

Questions about ijfw-core.

Which coding agents can use ijfw-core?
ijfw-core 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.