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.
Agent
Deep reasoning agent. Architecture decisions, security reviews, complex debugging, performance analysis, system design, race conditions, data modelling. Use when getting it wrong has high cost.
Agent
Implementation agent for SINGLE-FILE mechanical work. Writing code, generating boilerplate, scaffolding components, implementing features from specs, writing tests, standard bug fixes. Escalates anything bigger.
Agent
Audits frontend dashboard surfaces for WCAG AA conformance. Trigger after any dashboard UI change.
Agent
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
Agent
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
Agent
Audit a marketing campaign plan for objective alignment, audience fit, channel coherence, and message consistency. Trigger before each campaign-execution wave.
Agent
Apply atomic per-finding code fixes triggered by code-review output. 3-tier verify (re-read → syntax-check → fallback). Defers logic-bug fixes to humans.
Agent
Use when producing a structured map of a codebase — tech stack, architecture, conventions, and entry points — for downstream phases to consume.
Agent
Review individual marketing-copy pieces for tone, clarity, CTA strength, and conversion fundamentals. Trigger per piece pre-publish.
Agent
Use when managing a multi-cycle debug session that needs checkpoint/continuation across context resets.
Agent
Use when investigating a bug using the scientific method with hypothesis tracking.
Agent
Flag publishConfig drift, lock-in version skew, dep version mismatches. Trigger before any release wave.
Agent
Critique UI/visual design artefacts on hierarchy, contrast, alignment, consistency, and intent. Trigger per design review pass.
Agent
Use when a phase has ambiguities, gray areas, or unresolved decisions that need adaptive interrogation before SPEC can lock. Dispatched by ijfw-spec-phase, but can be called directly when the user says 'discuss this phase', 'what's unclear', 'interrogate the ambiguities', 'help me decide', '/ijfw-discuss-phase'.…
Agent
Verify factual claims in generated docs against live code. Trigger after doc generation in plan/handoff/CHANGELOG steps.
Agent
Writes/updates CHANGELOG.md + README.md from commit log + handoff. Trigger before ship-gate.
Agent
Pre-flight canonical install/update/uninstall in scratch tmpdir scoped to diff. Run before ship-gate.
Agent
Use when dispatching an implementation subagent that may hit issues requiring auto-fix vs ask-architectural decisions.
Agent
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
Agent
Verify E2E flows that span multiple subagent worktrees after Phase D wiring.
Agent
Sentence-level line editing pass for prose: rhythm, clarity, repetition, dialogue tags. Trigger after a draft is content-complete.
Agent
Tally session token cost vs milestone budget. Warn when a phase is on track to exceed allocation.
Agent
Maintain a canonical lore/world bible — characters, places, rules, factions. Source of truth for continuity checks.
Agent
Audit research method, bias surface, source quality, and traceability for a single research artefact. Trigger per artefact pre-publish.