Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add o-samoilov/quasar-graph/plugin install quasar-graphWrote 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/o-samoilov/quasar-graph/scan)<a href="https://agentmods.dev/skills/o-samoilov/quasar-graph/scan"><img src="https://agentmods.dev/badge/skills/o-samoilov/quasar-graph/scan/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/o-samoilov/quasar-graph/scan"><img src="https://agentmods.dev/badge/skills/o-samoilov/quasar-graph/scan.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 | $0.00045 | $0.10929 |
| Opus 5 | $0.00023 | $0.05464 |
| Sonnet 5 | $0.00009 | $0.02186 |
| Haiku 4.5 | $0.00005 | $0.01093 |
Grade A, and why
scan 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 9d 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/quasar-graph:scan
Orchestrate a scan of a directory containing the user's projects: catalog, deep analysis, resource aggregation, pre-upload review, and upload to the backend.
Inputs
The scan asks for inputs in this order:
- Session — new scan or resume of an existing one, chosen in the Session step below. Comes first because it determines
session_dirand whether this is a resume. Asession_idpassed explicitly in the invocation skips the choice. - Backend project + graph — chosen interactively in Phase 0 (project, then new/existing graph). This binds the scan before anything is cataloged.
scan_dir— absolute path to the directory to scan (containing the projects). Asked only after the backend binding, at the start of Phase 1. This is the scan target; nothing is written here.
The chosen project_id and graph_id are stored in manifest.backend and drive the upload in Phase 4. If the quasar-graph MCP server is unavailable, Phase 0 is skipped (offline mode): the scan still asks for scan_dir, writes all markdown to disk, and the upload is skipped.
Graph model (canonical statement — the phases below reference it, do not restate it). The scan produces the logical + ingress overlay model: logical dependency edges (who calls / needs whom — for illustration, client → api, api → db) plus the gateway/ingress routing path as a separate routes edge class (illustration: traefik → nginx → api — the gateways sit INSIDE the traffic path). The overlay is purely additive over the SAME logical dependency edges: it never removes or rewrites one (a direct client → api stays even when the routed path is also drawn), and if the scan finds no environment with a gateway it is simply a no-op. There is no toggle — the routing layer is always emitted. Operational rules live in Phase 3 (§ ingress overlay).
The scan output is always written under the current working directory (cwd) where the user launched the agent session — NOT inside scan_dir. cwd and scan_dir are often different directories. session_dir is derived from cwd + session_id and is therefore known before scan_dir is.
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.
- 9d ago First seen · 411 lines · 45 tokens per session scan A 94ee870edd14
scan is a skill published in the GitHub repository o-samoilov/quasar-graph (3 stars, last pushed 26d ago), licensed MIT. It adds 45 tokens to every session and 10,929 once invoked, about $0.0002 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
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
drawio-skill
Create, edit, synchronize, inspect, test, and publish editable draw.io diagrams. Use when the user explicitly requests draw.io/diagrams.net, needs a polished architecture, ERD, UML, sequence, C4, SysML, BPMN, network, swimlane, ML, or infrastructure diagram, wants code/IaC/SQL/OpenAPI converted into a diagram, or…
architecture-diagram
Create a professional, dark-themed software/system architecture diagram as a single self-contained HTML file with inline SVG. Use when asked to visualize system components, layers, services, or how parts of a codebase fit together.
diagram-design
A design guide for creating downloadable diagrams as HTML pages or standalone SVG files. It covers architecture, process, sequence, data, timeline, swimlane, quadrant, and statistical diagrams, including selected Mermaid and Draw.io imports.
archscribe
A tool for turning technical descriptions, articles, processes, or reference images into hand-drawn-style diagrams. It can produce editable Excalidraw diagrams, image and video previews, and interactive HTML.
architecture-drawer
Use when asked to draw system architecture diagrams, generate technical architecture SVGs, or export architecture diagrams to editable PowerPoint presentations. Supports multi-layer diagrams with automatic layout validation and scoring (16-dimension evaluator catches collisions, overlaps, dangles, crossings, palette…