Comprehensive codebase assessment for agent and production readiness. Scans 8 pillars (48 criteria), verifies commands work, checks GitHub settings. Reports everything, fixes agent readiness only. Triggers on literal `/flux:prime`.
From fluxnpx claudepluginhub nairon-ai/flux --plugin fluxThis skill uses the workspace's default tool permissions.
pillars.mdremediation.mdworkflow.mdDesigns and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Comprehensive codebase assessment inspired by Factory.ai's Agent Readiness framework.
Role: readiness assessor, improvement proposer Goal: full visibility into codebase health, targeted fixes for agent readiness
| Category | Pillars | What Happens |
|---|---|---|
| Agent Readiness | 1-5 (30 criteria) | Scored, maturity level calculated, fixes offered |
| Production Readiness | 6-8 (18 criteria) | Reported for awareness, no fixes offered |
This gives you full visibility while keeping remediation focused on what actually helps agents work.
Agents waste cycles when:
These are environment problems, not agent problems. Prime helps fix them.
Prime scans the codebase for cloud providers (Vercel, Railway, Neon, Supabase, Cloudflare, AWS, Stripe, etc.) and recommends MCPs or CLIs that give agents direct access. This means agents can deploy, query databases, check logs, and manage secrets without the user needing to open provider dashboards.
On entry, set the session phase:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
$FLUXCTL session-phase set prime
On completion, reset to idle:
$FLUXCTL session-phase set idle
Full request: $ARGUMENTS
Accepts:
--report-only or report only (skip remediation, just show report)--fix-all or fix all (apply all agent readiness fixes without asking)Examples:
/flux:prime/flux:prime --report-only/flux:prime ~/other-project| Pillar | What It Checks |
|---|---|
| 1. Style & Validation | Linters, formatters, type checking, pre-commit hooks |
| 2. Build System | Build tools, commands, lock files, monorepo tooling |
| 3. Testing | Test framework, commands, coverage, verification |
| 4. Documentation | README, CLAUDE.md, setup docs, architecture |
| 5. Dev Environment | .env.example, Docker, devcontainer, runtime version |
| Pillar | What It Checks |
|---|---|
| 6. Observability | Logging, tracing, metrics, error tracking, health endpoints |
| 7. Security | Branch protection, secret scanning, CODEOWNERS, Dependabot |
| 8. Workflow & Process | CI/CD, PR templates, issue templates, release automation |
Read workflow.md and execute each phase in order.
Key phases:
.flux/brain/codebase/architecture.md as the canonical whole-product map/flux:ruminate immediately as part of prime — not as a separate workflow suggestion.Prime's scout fan-out should apply flux-parallel-dispatch: launch all read-only, independent scouts together; do not serialize them.
| Level | Name | Description | Score |
|---|---|---|---|
| 1 | Minimal | Basic project structure only | <30% |
| 2 | Functional | Can build and run, limited docs | 30-49% |
| 3 | Standardized | Agent-ready for routine work | 50-69% |
| 4 | Optimized | Fast feedback loops, comprehensive docs | 70-84% |
| 5 | Autonomous | Full autonomous operation capable | 85%+ |
Level 3 is the target for most teams. Don't over-engineer.
| Pillars | Category | Remediation |
|---|---|---|
| 1-5 | Agent Readiness | ✅ Fixes offered via AskUserQuestion |
| 6-8 | Production Readiness | ❌ Reported only, address independently |
tooling-scout — linters, formatters, pre-commit, type checkingclaude-md-scout — CLAUDE.md/AGENTS.md analysisenv-scout — environment setuptesting-scout — test infrastructurebuild-scout — build systemdocs-gap-scout — README, ADRs, architectureobservability-scout — logging, tracing, metrics, healthsecurity-scout — GitHub settings, CODEOWNERS, secretsworkflow-scout — CI/CD, templates, automationAll 9 scouts run in parallel for speed.
ALWAYS run at the very end of command execution:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
UPDATE_JSON=$("$PLUGIN_ROOT/scripts/version-check.sh" 2>/dev/null || echo '{"update_available":false}')
UPDATE_AVAILABLE=$(echo "$UPDATE_JSON" | jq -r '.update_available')
LOCAL_VER=$(echo "$UPDATE_JSON" | jq -r '.local_version')
REMOTE_VER=$(echo "$UPDATE_JSON" | jq -r '.remote_version')
If update available, append to output:
---
Flux update available: v${LOCAL_VER} → v${REMOTE_VER}
Update Flux from the same source you installed it from, then restart your agent session.
---