The framework client-facing teams use to build internal & client apps with AI. Two agents — a Product Owner that advises what to build, and an AI Developer that ships it. Built by FuseBase.
Skill Claude CodeCodex
ALWAYS load at session start; mandatory, never on-demand. After self-attesting, Read references/ .md for your role (Product Owner / AI Developer / Architect / Deploy phase) — don't-list + refusal phrasing. Shared-protocol prohibitions and the FR-24 write-time digest stay resident here; bodies lazy-load from…
Skill Claude CodeCodex
Use when changes touch auth, permissions, secrets, env files, deploy config, external messages, data export/import, production DB writes, or customer-visible behavior; surfaces sensitive-path findings + approval-required list. Do NOT use as general code review.
Skill Claude CodeCodex
Use when the operator asks to create, update, import, analyze, or preserve a reusable skill or recurring instruction pattern. Do NOT use for one-off ticket work, ordinary code implementation, problem-catalog incidents, or copying external skill text verbatim.
Skill Claude CodeCodex
Use when Product Owner defines smoke prompts or deploy handoffs, and when AI Developer / Deploy phase executes post-deploy smoke. Do NOT use for pre-deploy unit/integration/source gates alone; smoke means proving the operator-visible outcome on the deployed surface with ground-truth diagnostics.
Skill Claude CodeCodex
Use when the operator explicitly asks for delegation, subagents, parallel agents, or when an AI Developer has independent T-task slices that can safely run in parallel. Do NOT use for simple edits, immediate blocking work, deploy commands, production side effects, or Product Owner code-writing.
Skill Claude CodeCodex
Use when implementing, debugging, or running long tool-using work sessions, or when the operator asks about "token waste", "session cost", "why is this so expensive", or runs "/token-waste-audit" — delivers FR-26's execution-time economy rules (scoped reads, no re-reads of unchanged in-context files, two-strike retry…
Skill Claude CodeCodex
Use when code changes need a gate report, operator asks "is this ready?", or a single observed failure needs reproducibility check; runs lint/typecheck/tests, smoke, probes, reproducibility-before-fix. Do NOT approve deploy (that's release-deploy-reporting).
Skill Claude CodeCodex
Use before committing a bug fix or improvement, when a fix is non-trivial, or when the same area has been patched before. Operationalizes FR-20 — zoom out to root cause before applying a narrow patch. Do NOT use for trivial typo/format edits, for net-new feature work with no prior code (nothing to zoom out from), or…
Plugin Claude Code
The framework client-facing teams use to build internal and client apps with AI. Two agents (Product Owner + AI Developer) run a disciplined spec-to-deploy lifecycle, packaged with FuseBase Apps domain skills. Closes the gaps that break real AI app development: drift, context rot, scope creep, unreliable hand-offs.
Agent Claude Code
Use this agent to execute a Fusebase Flow AI Developer or Deploy-phase handoff. Invoke with docs/tmp/handoff/ - -implement.md to attest as AI Developer and run the task chain (one task = one commit, stop at the verification gate), including approved framework skill edits when scoped. Invoke with docs/tmp/handoff/ …
Agent Claude Code
Run this agent when the user wants to create or update an app. It analyzes the user's requirements and produces a detailed technical architecture plan — data model, backend needs, permissions, UI structure — that the main coding agent will implement.
At most 3 mods per repository are shown here — the rest are on their repository pages: