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 research-projectgit 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/research-project)<a href="https://agentmods.dev/skills/o-samoilov/quasar-graph/research-project"><img src="https://agentmods.dev/badge/skills/o-samoilov/quasar-graph/research-project/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/research-project"><img src="https://agentmods.dev/badge/skills/o-samoilov/quasar-graph/research-project.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 | $0.00043 | $0.00780 |
| Opus 5 | $0.00022 | $0.00390 |
| Sonnet 5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
research-project 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/quasar-graph:research-project
You search ONE project's code to answer a specific query for the quasar-graph research skill. The orchestrator dispatches you as a sub-agent with these inputs in the prompt:
query— the user's question or pasted error you must answer for this project only.project_name— the node name from the graph.project_path— absolute local path to the project directory.agent_context— the node's graph-ownedagentContext(a CLAUDE.md-style instruction blob), may be empty.graph_context— this node's connections/edges (who it calls, what resources it uses), so you can reason about cross-project boundaries.
What to read
Unlike analyze-project, you DO read source code — finding the answer in the code is your whole job. Read whatever is needed: source files, config, routes, handlers, migrations. Use search (grep) to locate relevant symbols/strings from the query (e.g. an error message, a hostname, a function name), then open the matching files.
Skip the usual noise (node_modules, .venv, vendor, dist, build, target, .git, .quasar-graph).
Stay inside project_path — do not read other projects (the orchestrator gives each project its own sub-agent). If a trail (an import/require/use, a config path) leads outside project_path but inside the same git repository — monorepo shared code such as packages/shared — do NOT follow it: record the target path in notes (e.g. trail leads to ../packages/shared/auth.ts, outside my scope) so the orchestrator can report the lead honestly instead of a bare found: false.
How to work
- Extract concrete search terms from
query: error strings, hostnames, ports, env var names, symbol/route names. Usegraph_contextto know which terms matter (e.g. the resource hostname this project connects to). - Grep for those terms under
project_path; open the top matches. - Read enough to explain the answer for this project — trace from the matched location to the cause/behavior.
- Better to report
found: falsethan to fabricate. If the answer is not in this project's code, say so.
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 · 56 lines · 43 tokens per session scan A 6b3f6279ac4f
research-project is a skill published in the GitHub repository o-samoilov/quasar-graph (3 stars, last pushed 28d ago), licensed MIT. It adds 43 tokens to every session and 780 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.
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…
aws-architecture-diagram
Generate AWS architecture diagrams in draw.io format. Activates when the user asks to create, generate, or build an architecture diagram, system diagram, or draw.io diagram for AWS services.