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 sfc-gh-abannerjee/SnowGram --skill standalonegit clone --depth 1 https://github.com/sfc-gh-abannerjee/SnowGramWrote 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/sfc-gh-abannerjee/snowgram/standalone)<a href="https://agentmods.dev/skills/sfc-gh-abannerjee/snowgram/standalone"><img src="https://agentmods.dev/badge/skills/sfc-gh-abannerjee/snowgram/standalone/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/sfc-gh-abannerjee/snowgram/standalone"><img src="https://agentmods.dev/badge/skills/sfc-gh-abannerjee/snowgram/standalone.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 | $0.00066 | $0.02419 |
| Opus 5 | $0.00033 | $0.01210 |
| Sonnet 5 | $0.00013 | $0.00484 |
| Haiku 4.5 | $0.00007 | $0.00242 |
Grade A, and why
snowflake-architecture-diagram-standalone 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 8d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standalone mode
Generate exportable Snowflake architecture diagrams without needing a deployed SnowGram agent or any Snowflake connection. The default path composes a fresh diagram from flow_builder informed by cortex search docs and Snowflake-expert SME skills. The 14 bundled reference-architecture templates serve as fallbacks for prompts that cleanly match a known pattern (e.g. "medallion lakehouse with bronze/silver/gold").
Design rule (enforced by the rule store):
Templates are FALLBACKS, not the default generation path. Generate from-scratch (rich-state authoring) when the prompt does not closely match a known template pattern. Only fall back to a template when the prompt's intent maps cleanly onto one of the 14 reference architectures, AND in that case still apply prompt-driven customizations rather than emitting the template verbatim.
Path resolution (do this once)
This sub-skill uses $SKILL_DIR/... paths. Resolve them by sourcing the canonical helper:
source "<SKILL_BASE_DIR>/assets/scripts/skill_paths.sh"
# Sets $SKILL_DIR, $TEMPLATES_DIR, $COMPOSER_DIR, $VIEWER_DIR, $SCRIPTS_DIR, $STATE_FILE.
For Python helpers, import assets/scripts/skill_paths.py analogously. The parent SKILL.md shows the importlib pattern.
Workflow
Step 1 — Gather domain knowledge (PRIMARY, not optional)
Quality of the rendered diagram depends on having current Snowflake best-practice context BEFORE composition. Skip this step ONLY for trivial / one-off requests; for any production-quality diagram, do all three sub-steps.
1a. Detect pipeline type
PIPELINE_TYPE=$(python3 "$COMPOSER_DIR/intent_router.py" --detect-type "<user prompt>" | python3 -c "import sys,json;print(json.load(sys.stdin)['pipeline_type'])")
PIPELINE_TYPE is one of: medallion | streaming | iot | batch | security | generic.
1b. Run targeted documentation queries
python3 "$COMPOSER_DIR/intent_router.py" --queries-for "$PIPELINE_TYPE"
# → 3 queries to feed cortex search docs
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.
- 8d ago First seen · 193 lines · 66 tokens per session scan A fe9e76eb50e9
snowflake-architecture-diagram-standalone is a skill published in the GitHub repository sfc-gh-abannerjee/SnowGram (2 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 2,419 once invoked, about $0.0003 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
slides
Build a Grida slides deck — a .canvas bundle in slides mode whose pages are SVG documents (16:9, one SVG per slide). Use when creating a presentation, pitch deck, slideshow, or talk.
dotcanvas
Author and edit a Grida .canvas board — a .canvas.json manifest plus document files (references, generated images, notes) placed on an infinite canvas. Use when working on a .canvas bundle or arranging visuals/design work spatially. For a linear deck/presentation, use the slides skill instead.
datamodellm
Create visual data models for database schemas using Nimbalyst's DataModelLM editor. Use when the user wants to design a data model, database schema, entity relationship diagram, or Prisma schema.
svg
Author and edit .svg files in a Grida editor session — live-canvas binding, SVG output style, and parse-error recovery. Use when creating or modifying an SVG document.
er-diagrams
Create animated entity-relationship and database schema diagrams using the Excalimate MCP server. Use when asked to visualize database schemas, data models, table relationships, foreign keys, entity relationships, or any structured data design with tables and their connections.
run402
Provision Postgres + REST API + auth + content-addressed storage + serverless functions + email — paid with x402 USDC on Base. Prototype tier is free on testnet. Use when the user asks to build a webapp, deploy a site, create a database, generate images, or mentions Run402.