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 connected-cligit 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/connected-cli)<a href="https://agentmods.dev/skills/sfc-gh-abannerjee/snowgram/connected-cli"><img src="https://agentmods.dev/badge/skills/sfc-gh-abannerjee/snowgram/connected-cli/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/connected-cli"><img src="https://agentmods.dev/badge/skills/sfc-gh-abannerjee/snowgram/connected-cli.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 | $0.00040 | $0.01320 |
| Opus 5.5 | $0.00016 | $0.00528 |
| Sonnet 5.5 | $0.00008 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
snowflake-architecture-diagram-connected-cli 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 2mo 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connected-CLI mode
Calls the deployed SnowGram agent directly via the Cortex Agents API and renders the response in the bundled lightweight viewer. No Next.js frontend needed.
Prerequisites
- Active
cortexconnection (set viacortex connections set <name>) - Agent
SNOWGRAM_DB.AGENTS.SNOWGRAM_AGENTdeployed and reachable from the active role - Function grants verified during the parent skill's mode-detection probe
Path resolution (do this once)
This sub-skill uses $SKILL_DIR/... paths. Resolve them by sourcing the canonical helper. The absolute path to that helper is <SKILL_BASE_DIR>/assets/scripts/skill_paths.sh, where <SKILL_BASE_DIR> is the path the skill loader prints as Base directory for this skill: when this skill is loaded (or the path returned by cortex skill list for snowflake-architecture-diagram).
source "<SKILL_BASE_DIR>/assets/scripts/skill_paths.sh"
# Now: $SKILL_DIR, $TEMPLATES_DIR, $COMPOSER_DIR, $VIEWER_DIR, $SCRIPTS_DIR,
# $STATE_FILE are all set. See the parent SKILL.md for the full table.
For Python helpers, import assets/scripts/skill_paths.py analogously. The parent SKILL.md shows the importlib pattern.
Workflow
Step 1: Invoke the agent
cortex agents run SNOWGRAM_DB.AGENTS.SNOWGRAM_AGENT "<user's prompt>"
Capture stdout. The agent typically returns:
- A short overview paragraph
- A Mermaid code block (delimited by
```mermaid/```) - Optionally a JSON block with components / connections (also fenced)
- Best-practice bullets and citations
Step 2: Extract Mermaid
Use a regex to extract the first fenced Mermaid block:
import re
m = re.search(r'```mermaid\s*\n(.*?)\n```', agent_output, re.DOTALL)
mermaid = m.group(1) if m else None
If Mermaid is present: continue to Step 3.
If Mermaid is missing (agent answered in prose only):
- The agent's tool description may not be enforcing Mermaid output (see
snowgram-agentskill for the fix) - Fall through to standalone mode using the agent's textual response as a hint:
- Pass the agent's response to a freeform composer call: extract any component names mentioned, look them up in
$SKILL_DIR/assets/component_synonyms.json, and feed BLOCK_IDs tocomposer.py - Tag the result
source: "connected-cli:fallback-to-standalone"
- Pass the agent's response to a freeform composer call: extract any component names mentioned, look them up in
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.
- 2mo ago First seen · 134 lines · 40 tokens per session scan A bcbc4a1d5349
snowflake-architecture-diagram-connected-cli is a skill published in the GitHub repository sfc-gh-abannerjee/SnowGram (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,320 once invoked, about $0.0002 per session on Opus 5.5. 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.
snowflake-architecture-diagram-connected-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| snowflake-architecture-diagram-connected-clisfc-gh-abannerjee/SnowGram | Skill | 2 | 1mo ago | MIT | A | 40 | Claude Code, Codex |
| slidesgridaco/grida | Skill | 2.7k | yesterday | Apache-2.0 | A | 46 | Claude Code, Codex |
| dotcanvasgridaco/grida | Skill | 2.7k | yesterday | Apache-2.0 | A | 69 | Claude Code, Codex |
| datamodellmnimbalyst/nimbalyst | Skill | 2.0k | 2d ago | MIT | A | 45 | Claude Code, Codex |
| svggridaco/grida | Skill | 2.7k | yesterday | Apache-2.0 | A | 39 | Claude Code, Codex |
| er-diagramsexcalimate/excalimate | Skill | 100 | 5d ago | MIT | A | 52 | Claude Code, Codex |
| dashboard-designDeepSQLAI/deepsql | Skill | 40 | 5d ago | Apache-2.0 | A | 43 | Claude Code, Codex |