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 gnurio/nurijanian-skills --skill workflow-trellisgit clone --depth 1 https://github.com/gnurio/nurijanian-skillsWrote 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/gnurio/nurijanian-skills/workflow-trellis)<a href="https://agentmods.dev/skills/gnurio/nurijanian-skills/workflow-trellis"><img src="https://agentmods.dev/badge/skills/gnurio/nurijanian-skills/workflow-trellis/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/gnurio/nurijanian-skills/workflow-trellis"><img src="https://agentmods.dev/badge/skills/gnurio/nurijanian-skills/workflow-trellis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Privilege Escalation · line 354 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
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 | $0.00102 | $0.05167 |
| Opus 5 | $0.00051 | $0.02583 |
| Sonnet 5 | $0.00020 | $0.01033 |
| Haiku 4.5 | $0.00010 | $0.00517 |
Grade A, and why
workflow-trellis 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 11d 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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Trellis
Use this skill to turn messy workflow evidence into a clear representation of how the work actually functions, what obligation forces it to exist, where the representation is fragmented, and where AI can be inserted safely.
The central thesis: do not start with "AI can automate X." Start by representing the work. Once the obligation, entities, states, deadlines, dependencies, evidence, fragments, and human judgment points are visible, the AI opportunities become obvious and less hand-wavy.
The output should make the workflow visible as an object. Tables are not decoration here; they force the analysis to separate the parts of the work that get blurred in prose. Every deep workflow model must include the required tables, a workflow diagram, an Intuition Gained section, and a Product Implications section.
When Starting
If the user provides interviews, transcripts, notes, support tickets, customer research, or a domain description, treat that material as evidence. Extract workflows from it rather than brainstorming from scratch.
Ask at most three clarifying questions only when the answer materially changes the representation:
- Which workflow or user segment should be modeled first?
- Is the goal product strategy, AI feature design, customer discovery, or startup exploration?
- Should the output favor breadth across many workflows or depth on one workflow?
If the user sounds like they want momentum, skip questions and state assumptions.
Core Lens
Analyze workflows through three gates:
- Durable obligation: The work must exist because law, money, customers, operations, professional standards, auditability, or accountability demand it.
- Fragmented representation: The truth of the work must be split across spreadsheets, emails, PDFs, bank portals, desktop apps, messages, forms, humans, vendors, customers, or legacy systems.
- Hated execution burden: The recurring work must be tedious, anxiety-producing, deadline-bound, error-prone, or socially annoying enough that users already complain about it.
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.
- 11d ago First seen · 472 lines · 102 tokens per session scan A 34f48da43c02
workflow-trellis is a skill published in the GitHub repository gnurio/nurijanian-skills (105 stars, last pushed 29d ago), licensed MIT. It adds 102 tokens to every session and 5,167 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…