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 agentmods add skills/anomalyarmor/agents/connectnpx skills add anomalyarmor/agents --skill connectgit clone --depth 1 https://github.com/anomalyarmor/agentsWhat 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 | $0.00032 | $0.01114 |
| Opus 5 | $0.00016 | $0.00557 |
| Sonnet 5 | $0.00006 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
armor-connect 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Data Source
Guide users through connecting a new data source (database, warehouse) to AnomalyArmor.
Prerequisites
- AnomalyArmor API key configured (
~/.armor/config.yamlorARMOR_API_KEYenv var) - Python SDK installed (
pip install anomalyarmor) - Database credentials ready
When to Use
- "Connect my Snowflake warehouse"
- "Add my PostgreSQL database"
- "Setup Databricks connection"
- "Connect a new data source"
Supported Data Sources
snowflake- Snowflake Data Cloudpostgresql- PostgreSQLdatabricks- Databricksbigquery- Google BigQueryredshift- Amazon Redshiftmysql- MySQLclickhouse- ClickHouse
Steps
- Ask user for data source type if not specified
- Collect connection configuration (credentials, host, database, etc.)
- Create the asset with
client.assets.create() - Test the connection with
client.assets.test_connection() - If successful, trigger schema discovery with
client.assets.trigger_discovery() - Track discovery progress with
client.jobs.status()
Example Usage
Connect Snowflake
from anomalyarmor import Client
import time
client = Client()
# Create the asset
asset = client.assets.create(
name="Analytics Warehouse",
source_type="snowflake",
connection_config={
"account": "abc123.us-east-1",
"warehouse": "COMPUTE_WH",
"database": "ANALYTICS",
"user": "anomalyarmor_user",
"password": "your_password", # Or use key pair auth
"role": "ANOMALYARMOR_ROLE" # Optional
},
description="Main analytics data warehouse"
)
print(f"Created asset: {asset.id}")
# Test connection
result = client.assets.test_connection(asset.id)
if result.success:
print("Connection successful!")
else:
print(f"Connection failed: {result.error_message}")
exit(1)
# Trigger schema discovery
job = client.assets.trigger_discovery(asset.id)
print(f"Discovery started: {job.job_id}")
# Wait for discovery to complete
while True:
status = client.jobs.status(job.job_id)
print(f"Discovery progress: {status.get('progress', 0)}%")
if status.get('status') in ('completed', 'failed'):
break
time.sleep(5)
if status.get('status') == 'completed':
print("Schema discovery complete!")
else:
print(f"Discovery failed: {status.get('error')}")
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.
- yesterday First seen · 189 lines · 32 tokens per session scan A f6ef9413322c
armor-connect is a skill published in the GitHub repository anomalyarmor/agents (1 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 1,114 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.