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 AnthonyAlcaraz/agentic-graph-rag-skills --skill workflow-agent-spectrum-classifiergit clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-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/anthonyalcaraz/agentic-graph-rag-skills/workflow-agent-spectrum-classifier)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/workflow-agent-spectrum-classifier"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/workflow-agent-spectrum-classifier/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/anthonyalcaraz/agentic-graph-rag-skills/workflow-agent-spectrum-classifier"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/workflow-agent-spectrum-classifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00186 | $0.02056 |
| Opus 5 | $0.00093 | $0.01028 |
| Sonnet 5 | $0.00037 | $0.00411 |
| Haiku 4.5 | $0.00019 | $0.00206 |
Grade A, and why
workflow-agent-spectrum-classifier 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 10d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow-Agent Spectrum Classifier
Overview
Ch1 rejects "is it an agent or not" as the wrong question. Following Andrew Ng ("systems can be agent-like to different degrees") and Anthropic's workflow-vs-agent distinction, it places systems on a continuous spectrum:
- Workflow end — "predefined execution paths: orchestrated sequences that follow explicit instructions." Reliable and deterministic, limited adaptability. Chapter examples: a FAQ generator, a fund-analysis app.
- Agent end — systems that "determine processes dynamically, providing flexibility at the cost of predictability." Chapter examples: coding agents, deep research agents.
- Blended middle — "deterministic workflows with nondeterministic LLMs inserted at key points," with humans in the loop where judgment is required. Chapter example: an investment firm's market-commentary report — the LLM retrieves, analyzes, and submits; humans review for compliance and submit to regulators.
The placement is grounded in the three dimensions of agency, which "exist on sliding scales, not as binary attributes":
- Autonomy — degree of independent decision-making without external direction.
- Action — ability to execute decisions that affect the environment. "Without this capability to effect change, you have an assistant or advisor, not an agent."
- Authority — scope and limitations of permitted actions. (Ch1's real-estate-agent example: high autonomy to market a property, little authority over price.)
When a system operates across these dimensions, four capabilities emerge: autonomous decision-making, contextual understanding, strategic tool utilization, and memory persistence. The skill reports them alongside the band.
When to Use
- Right-sizing an architecture: deterministic workflow vs blended human-in-the-loop vs full agent
- Settling a "is this really an agent?" debate with a shared rubric
- Auditing whether a "read-only advisor" is being over-sold as an agent (the action test)
- Teaching the three agency dimensions with concrete placements
What ships with it
3 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.
- 10d ago First seen · 155 lines · 186 tokens per session scan A 1f04f4ddedc4
workflow-agent-spectrum-classifier is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 2,056 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
jurisd-research
Expert Australian/NZ legal research and AGLC4 citation using the jurisd MCP server. Use when finding cases or legislation (AustLII), looking up a provision offline, formatting or resolving citations, building a pinpoint, tracing who-cites-what, or producing an AGLC4 bibliography. Triggers on case law, legislation…
repo_search
Search repository text through a deterministic first-class fak command.
container-manager-kg-ingestion
Snapshot a host's Docker/Podman/Swarm inventory into the epistemic-graph knowledge graph as typed OWL nodes via the container-manager-mcp MCP server — containers, images, volumes, networks, swarm services and nodes, with their :usesImage / :runsOn / :builtFrom links. Use when the agent must record live container state…
cortex-design
Use this skill to generate well-branded interfaces and assets for Cortex, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.