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 o-samoilov/quasar-graph --skill editgit clone --depth 1 https://github.com/o-samoilov/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/edit)<a href="https://agentmods.dev/skills/o-samoilov/quasar-graph/edit"><img src="https://agentmods.dev/badge/skills/o-samoilov/quasar-graph/edit.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.01511 |
| Opus 5 | $0.00037 | $0.00756 |
| Sonnet 5 | $0.00015 | $0.00302 |
| Haiku 4.5 | $0.00007 | $0.00151 |
Grade A, and why
edit 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 7d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/quasar-graph:edit
Edit an existing backend graph directly: pull its full snapshot, change it in conversation, push it back. No scanning, no source-code reads. Requires the quasar-graph MCP server (the graph lives on the backend — there is no offline mode).
The unit of work is the snapshot file <session_dir>/graph/graph.json: nodes (id, name, type, description, repoUrl, projectPath, agentContext, position, data, links) and edges (sourceNodeId, targetNodeId, type). push_graph recomputes deterministic ids from (graphId, type, name) and rewires edges, so in-file ids only need to be internally consistent.
Node type is a backend enum — the only valid values are project, service, database, external_api, admin_panel, gateway, cache, queue, storage, monitoring, auth_provider, cdn, library, search, realtime, other; pushing any other value is rejected with 422. Node data is one flat schema shared by all types — exactly five nullable fields (engine, port, hostname, technologies, packageName); any field is valid on any type, and keys outside the five are not persisted by the backend.
Conventions
Read references/conventions.md at the quasar-graph plugin root before acting. It defines the action vocabulary this skill is written in (selection prompt, edit the file, …) with its per-harness degradations, the selection UI rules, the login retry flow, and the repo identity & binding cache rules.
Fixed choices in this skill that always use a selection prompt: the bound-graph default offer (use bound graph / pick another), and the pre-push confirmation gate (push / keep editing / discard) — recommended/default option first.
Phase 0 — Bind a graph
- Confirm the
quasar-graphMCP tools are available. If not, report:Edit needs the quasar-graph MCP server (the graph lives on the backend). Enable it and retry.Then stop. - Authentication. On a
Not authenticated with the quasar-graph backendfailure, run the login retry flow from the conventions file. If it still fails, stop (edit has no offline mode). - Default from the binding cache. Run
git remote get-url originin the invocation directory and normalize the URL per the conventions file. If~/.quasar-graph/cache/bindings.jsonhas an entry for it, offer that graph first as the default (selection prompt: use it / pick another) — an entry naming several graphs gets one option per graph, labeled the same way. The cache lookup is read-only; ownership stays with thebind_contextMCP tool. If pulling a cache-default graph then fails because it no longer exists on the backend, report it, leave the cache untouched, and fall back to step 4 for manual selection. - Otherwise (or if the user picks another): call
list_workspacesandlist_projects, ask which project (selection UI rules, incl. workspace labeling), thenlist_graphswithproject_idand ask which graph — showname / nodes_count / scanned_atper option. If either list is empty, report it (for an empty graph list suggest/quasar-graph:scan) and stop. Capturegraph_id.
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.
- 7d ago First seen · 53 lines · 74 tokens per session scan A 238099c27a63
edit is a skill published in the GitHub repository o-samoilov/quasar-graph (3 stars, last pushed 25d ago), licensed MIT. It adds 74 tokens to every session and 1,511 once invoked, about $0.0004 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…