Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jonathan-vella/apex-accelerator --skill workflow-enginegit clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jonathan-vella/apex-accelerator/workflow-engine)<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/workflow-engine"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/workflow-engine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/workflow-engine"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/workflow-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.01385 |
| Opus 5 | $0.00047 | $0.00692 |
| Sonnet 5 | $0.00019 | $0.00277 |
| Haiku 4.5 | $0.00009 | $0.00138 |
Grade A, and why
workflow-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Engine Skill
Provides a declarative, machine-readable workflow graph that the Orchestrator reads instead of relying on hardcoded step logic.
When to Use
- Orchestrator determining the next step after a gate
- Resuming a workflow via
apex-recall show <project> --json - Validating that all steps have proper dependencies and outputs
- Understanding fan-out (parallel sub-steps) and conditional routing
Rules
- DAG only — the workflow is a Directed Acyclic Graph; no cycles, no back-edges
- Source of truth is
templates/workflow-graph.json— the orchestrator reads this directly; do not encode workflow logic in agent prose - Gates are blocking — a
gatenode halts downstream execution until human approval is recorded in session state - IaC routing is conditional on
decisions.iac_tool— Step 3 → Step 4 / 5 / 6 routes to*-b(Bicep) or*-t(Terraform) - Fan-out children execute in parallel — Step 7 docs is the canonical example; do not serialize parallel children
- Edge conditions — use exactly one of
on_complete,on_skip,on_failper edge; ambiguity is a validation error - Schema evolution — bump
metadata.versionand followreferences/schema-evolution.mdrollback rules when changing the graph - Validation is enforced at three points — graph shape (
validate-workflow-graph.mjs), handoff buttons (validate-agents.mjs --only=workflow-handoffs), and gate-companion H2 sync (validate-artifacts.mjs)
Steps
Orchestrator protocol for routing the next step:
- Load
templates/workflow-graph.json - Read current state —
apex-recall show <project> --json→current_step - Find the matching node in the graph
- Check node status:
complete→ followon_completeedges → find next nodein_progress→ resume fromsub_stepcheckpointpending→ execute this nodeskipped→ followon_skipedges
- Apply IaC routing when present — read
decisions.iac_tooland pick the*-bor*-tbranch - If next is a
gate— present to user, wait for approval, record decision in session state - If next is a
subagent-fan-out— dispatch all children in parallel; collect results before continuing - Repeat until all nodes are complete or blocked
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 102 lines · 94 tokens per session scan A c1bb2d92066b
workflow-engine is a skill published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 5d ago), licensed MIT. It adds 94 tokens to every session and 1,385 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
ltx2
AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…