FerroxLabs/ijfw

Auto Memorize extracts lessons, errors, fixes, and user preferences from a session at the end and stores them as structured local memory. It asks for consent on first run and stays local unless an API model is configured.

Critique challenges decisions, surfaces assumptions, and offers concrete counter-arguments when someone asks for a second opinion or devil’s advocate. It also reframes non-trivial refactors toward the elegant solution before choosing a pragmatic fix.

IJFW AGENTS.md Manager maintains a project's canonical AGENTS.md file and its marker blocks. Use it when updating agent instructions or regenerating the file from IJFW-generated agent data.

IJFW Commit writes terse Conventional Commit messages with the right type, scope, and subject length. Use it when you need a clean git commit message and an optional follow-up critique run.

IJFW Compress reduces prose in memory or context files while preserving headings, code blocks, URLs, paths, commands, dates, versions, and technical terms. Use it when you need to cut tokens without changing code or meaning.

IJFW Compute runs sandboxed scripts for large or repetitive data tasks like log analysis, aggregation, deduping, and counting. It also supports indexing and searching findings so recurring questions can reuse prior results.

IJFW Core applies always-on output rules, mode routing, and context discipline for Claude Code interactions. Use it when you want terse, task-routed responses with optional smart, fast, deep, manual, or brutal modes.

IJFW Cross Audit generates a multi-model audit of a diff, file, brief, or artifact. Use it to get a second opinion, compare independent findings, or reconcile consensus across several model lineages.

IJFW Dashboard controls a local observability dashboard to start, stop, or check status. Use it to view session activity and live observations from Claude Code, Codex, and Gemini.

IJFW Design turns design requests into real HTML mockups, live previews, and durable design notes. Use it for UI, layout, accessibility, branding, and visual polish work.

IJFW Handoff generates a concise session handoff file and loads it on the next session start. Use it when ending work, hitting context limits, or resuming a paused task.

IJFW Metrics tracks session-level usage at stop time and summarizes tokens, agent activity, routing savings, and continuity. Use it when you want to review Claude Code performance with /ijfw-status.

IJFW New Milestone kicks off a scoped milestone cycle on an existing project and prepares planning artifacts. Use it to define the next release, chapter, wave, or design-system tier before execution.

IJFW New Project bootstraps a new project brief for software and non-software domains like books, campaigns, landing pages, design systems, and launches. Use it when starting from a vague idea and needing a confirmed brief plus next step.

IJFW Plan turns a brief or spec into a falsifiable PLAN.md with tasks, dependency waves, and success criteria. Use it when someone asks to plan work or wants the next execution steps after discovery or research.

IJFW Preflight runs 11 local quality checks in order and stops on blockers. Use it before release, after script or dependency changes, or in CI to validate the project.

IJFW Ship closes a release across software, books, campaigns, landing pages, or design systems. It checks the issue ledger and brief, then gates irreversible publish or deploy actions on a user push-word.

Ijfw Debug guides root-cause analysis with reproducible steps, hypothesis tracking, and fix verification. Use it when something is broken or not working and you need to isolate the cause.

Ijfw Recall surfaces relevant project memory at session start or when asked with recall-related prompts. It summarizes working and project memory entries and points to full text on request.

Ijfw Review checks code, prose, briefs, landing pages, and design artifacts for issues. Use it when you need severity-tagged feedback and a written REVIEW.md artifact.

Memory Audit scans .ijfw/memory files, classifies them by recency, and reports stale or archive candidates. Use it to review memory bloat before moving unused entries to archive.

Milestone Completion archives a finished milestone, generates a summary, and records learnings so the next milestone can be seeded. Use it when a top-level project unit is ready to ship and needs closure artifacts.

Milestone Summary produces a milestone onboarding document at .planning/<milestone>/SUMMARY.md. Use it to recap what shipped, what was deferred, and the key decisions for someone joining mid-stream.

Plan Check audits a plan before execution by tracing tasks to brief criteria, flagging scope leaks, and checking risk and dependency order. Use it when you want a decisive pass, flag, or block verdict before building.

Receiving Review helps you respond to code review comments with verify-then-reply rigor. Use it to agree and fix, disagree with evidence, or ask one specific clarifying question when feedback comes back.