ijfw
Local-first infrastructure for AI coding agents, providing shared memory, smart routing, multi-model cross-audits, and disciplined workflow skills such as commits, milestone archiving, and memory compression.
36 skills214
@ferroxlabs- 214Stars earned
- 1Plugin
- 36Skills
- 37Agents
- 22Commands
- 1MCP server
Plugins
1@ferroxlabsSkills
36ijfw-agents-md
Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent…
@ferroxlabsijfw-auto-memorize
Session-end auto-extraction of lessons, errors, fixes, and user feedback into structured memory. Fires at session end. Requires…
@ferroxlabsijfw-commit
Terse conventional commits. Trigger: commit, git commit, /ijfw-commit
@ferroxlabsijfw-complete-mileston…
Use when a milestone is shipping and you need to archive its artifacts, generate a summary, and seed the next milestone. Trigger:…
@ferroxlabsijfw-compress
Compress memory/context files into terse form. Trigger: /compress, compress file
@ferroxlabsijfw-compute
Use when the user says: 'compute', 'crunch this', 'analyze logs', 'aggregate the data', 'run a script', 'dedupe', 'count by',…
@ferroxlabsijfw-core
IJFW efficiency layer -- smart output, routing, context discipline. Always active. Trigger: any IJFW interaction. Disable: 'ijfw…
@ferroxlabsijfw-critique
Challenge decisions, surface counter-arguments, flag assumptions. Trigger: 'should I', 'is this right', 'critique', 'poke holes',…
@ferroxlabsijfw-cross-audit
Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second…
@ferroxlabsijfw-dashboard
Control the IJFW observation dashboard (start/stop/status). Trigger: 'ijfw dashboard', 'open dashboard', 'show observations',…
@ferroxlabsijfw-debug
Root-cause analysis with hypothesis tracking. Trigger: 'debug', 'broken', 'not working', 'fix this bug', /debug
@ferroxlabsijfw-design
Use when the user says: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look better', 'polish',…
@ferroxlabsAgents
37architect
AgentDeep reasoning agent. Architecture decisions, security reviews, complex
@ferroxlabsbuilder
AgentImplementation agent for SINGLE-FILE mechanical work. Writing code, generating boilerplate, scaffolding components, implementing…
@ferroxlabsijfw-accessibility-eng
AgentAudits frontend dashboard surfaces for WCAG AA conformance. Trigger after any dashboard UI change.
@ferroxlabsijfw-accessibility-rev…
AgentDesign-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
@ferroxlabsijfw-assumptions-analy…
AgentUse when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec…
@ferroxlabsijfw-campaign-strategi…
AgentAudit a marketing campaign plan for objective alignment, audience fit, channel coherence, and message consistency. Trigger before…
@ferroxlabsijfw-code-fixer
AgentApply atomic per-finding code fixes triggered by code-review output. 3-tier verify (re-read → syntax-check → fallback). Defers…
@ferroxlabsijfw-codebase-mapper
AgentUse when producing a structured map of a codebase — tech stack, architecture, conventions, and entry points — for downstream…
@ferroxlabsijfw-copy-reviewer
AgentReview individual marketing-copy pieces for tone, clarity, CTA strength, and conversion fundamentals. Trigger per piece…
@ferroxlabsijfw-debug-session-man…
AgentUse when managing a multi-cycle debug session that needs checkpoint/continuation across context resets.
@ferroxlabsijfw-debugger
AgentUse when investigating a bug using the scientific method with hypothesis tracking.
@ferroxlabsijfw-dep-audit
AgentFlag publishConfig drift, lock-in version skew, dep version mismatches. Trigger before any release wave.
@ferroxlabsCommands
22compress
CommandCompress a memory/context file into terse form. Saves ~40-50% tokens per session. Usage: /compress <filepath>
@ferroxlabsconsolidate
CommandDream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
@ferroxlabscross-audit
CommandSecond-model review. Picks an auditor (codex/gemini/opencode/aider/copilot), excludes the caller, writes a prompt to paste, reads…
@ferroxlabscross-critique
CommandAdversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux).…
@ferroxlabscross-research
CommandTwo-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via…
@ferroxlabsdoctor
CommandRun IJFW health check (files, MCP server, hooks, memory, caps, framing)
@ferroxlabshandoff
CommandGenerate or load a session handoff. Usage: /handoff [create|resume]
@ferroxlabsijfw
CommandIJFW command index. Groups commands by intent: Build / Remember / Ship / Review / Configure.
@ferroxlabsijfw-audit
CommandRun the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name]
@ferroxlabsijfw-execute
CommandJump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name]
@ferroxlabsijfw-help
CommandOpen the full IJFW guide. Terminal-paged by default, or rendered in a browser tab with `--browser`. Use when the user asks how to…
@ferroxlabsijfw-plan
CommandJump directly to the IJFW workflow Plan phase (Deep D3 / Quick Q2). Usage: /ijfw-plan [brief description of what to plan]
@ferroxlabsMCP server
1ijfw-memory
MCPShips with ijfw: IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart…
@ferroxlabsIs this you? Claim your profilePut a plugin at the top of Plugins, from $9