Agent
Audit a research project for question framing, methodology fit, source coverage, and synthesis integrity. Trigger before each synthesize or review wave.
Agent
Audit a research project for question framing, methodology fit, source coverage, and synthesis integrity. Trigger before each synthesize or review wave.
Agent
Review a business strategy or plan artefact for feasibility, downside math, risk surface, and metric realism. Trigger per artefact pre-decision.
Agent
Use when generating a ROADMAP.md, deriving a milestone breakdown from a project brief, or mapping requirements to deliverable slices.
Agent
Verify mitigations against handoff threat model exist in code. Run after each implementation wave.
Agent
Audit a business strategy artefact for objective alignment, stakeholder fit, decision quality, and execution coherence. Trigger before each decide or review wave.
Agent
Use when auditing implemented frontend code or visual artifacts against UI-SPEC.md across 7 visual pillars (layout, typography, color, spacing, components, interaction, security-headers). Produces UI-REVIEW.md with per-pillar PASS / FLAG / BLOCK verdicts and evidence.
Agent
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
Command
Compress a memory/context file into terse form. Saves 40-50% tokens per session. Usage: /compress.
Command
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
Command
Second-model review. Picks an auditor (codex/gemini/opencode/aider/copilot), excludes the caller, writes a prompt to paste, reads the response back. Usage: /cross-audit [--with | list | compare].
Command
Adversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux). Counter-args ranked by rebuttal survival score, not raw severity. Usage: /cross-critique [--with | list | compare].
Command
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage: /cross-research [--with | list | compare].
Command
Run IJFW health check (files, MCP server, hooks, memory, caps, framing).
Command
Generate or load a session handoff. Usage: /handoff [create|resume].
Command
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
Command
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].
Command
Open the full IJFW guide. Terminal-paged by default, or rendered in a browser tab with --browser. Use when the user asks how to use IJFW, what commands exist, or how to do something specific.
Command
Jump directly to the IJFW workflow Plan phase (Deep D3 / Quick Q2). Usage: /ijfw-plan [brief description of what to plan].
Command
Run the IJFW workflow Ship phase (Deep D6). Pre-flight, deploy, and close. Usage: /ijfw-ship.
Command
Run the IJFW workflow Verify phase (Deep D5). Full audit against the original brief. Usage: /ijfw-verify.
Command
IJFW command index. Groups commands by intent: Build / Remember / Ship / Review / Configure.
Command
List auto-extracted memory entries for review. Remove any with /ijfw memory forget .
Command
Grant or revoke consent for session-end auto-memorize. Usage: /memory-consent yes|no|ask.
Command
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.