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 install-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/install-project)<a href="https://agentmods.dev/skills/o-samoilov/quasar-graph/install-project"><img src="https://agentmods.dev/badge/skills/o-samoilov/quasar-graph/install-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/install-project"><img src="https://agentmods.dev/badge/skills/o-samoilov/quasar-graph/install-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 | $0.00051 | $0.01409 |
| Opus 5 | $0.00026 | $0.00705 |
| Sonnet 5 | $0.00010 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade C, and why
install-project scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **Non-standard (you DO NOT run — add to `proposed`):** `make <target>`, `./scripts/*.sh`, `curl ... | sh`, DB migrations, build/compile steps, or anything that is not purely dependency install. Include a short `rationa Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Non-standard (you DO NOT run — add to `proposed`):** `make <target>`, `./scripts/*.sh`, `curl ... | sh`, DB migrations, build/compile steps, or anything that is not purely dependency install. Include a short `rationa How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/quasar-graph:install-project
You install dependencies for ONE freshly cloned project for the quasar-graph clone skill. The orchestrator dispatches you as a sub-agent with these inputs in the prompt:
project_name(s)— the project name, or for a monorepo the list of contained project names.target_path— absolute path to the cloned directory (for a monorepo, the common-prefix directory).agent_context— the graph node's curated install/context blob, ornull. For a monorepo this is a list of{ name, agentContext }.
You do NOT prompt the user (you run inside a parallel batch). You run only known install commands and return everything else for the orchestrator to confirm.
What to read (config + docs only — NEVER source code)
Read only these, at or under target_path (depth 1–3, skipping node_modules, .venv, vendor, dist, build, target, .git):
- Container/build:
docker-compose*.yml,Dockerfile* - Task runners / docs:
Makefile,CLAUDE.md,AGENTS.md, rootREADME* - Manifests + lockfiles:
package.json,pnpm-lock.yaml,yarn.lock,package-lock.json,bun.lockb,composer.json,pyproject.toml,Pipfile,Pipfile.lock,requirements.txt,go.mod,Cargo.toml,pubspec.yaml,Gemfile - Env:
.env,.env.example,.env.*(names/structure only — never echo secret values)
Scripts referenced by a Makefile (scripts/*.sh) may be read so you can quote them to the user, but MUST NOT be executed by you. Do not read application source code.
How to decide the install command
Pick the install approach by this priority:
agent_context— trusted, curated. If it states how to install (e.g. "deps run in theappcontainer:docker compose run --rm app composer install"), follow it.- Project docs/config — a
Makefiletarget, adocker-compose.ymlservice, or a rootREADMEsetup section. (read these to learn the intended installer; a baremake <target>is still non-standard and goes toproposed). - Lockfile baseline — if nothing above is decisive, fall back to the manifest/lockfile at the root:
Signal at root Command pnpm-lock.yamlpnpm installyarn.lockyarn installbun.lockbbun installpackage-lock.jsonnpm cipackage.json(no lockfile)npm installpoetry.lock/pyproject.toml [tool.poetry]poetry installPipfile.lock/Pipfilepipenv installrequirements.txtpip install -r requirements.txtgo.modgo mod downloadCargo.tomlcargo fetchcomposer.jsoncomposer installpubspec.yaml(withflutter:→ flutter)dart pub get/flutter pub getGemfilebundle install
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 · 84 lines · 51 tokens per session scan C 5a8de6a6c285
install-project is a skill published in the GitHub repository o-samoilov/quasar-graph (3 stars, last pushed 27d ago), licensed MIT. It adds 51 tokens to every session and 1,409 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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…