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 Abilityai/abilities --skill connectgit clone --depth 1 https://github.com/Abilityai/abilitiesWrote 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/abilityai/abilities/connect)<a href="https://agentmods.dev/skills/abilityai/abilities/connect"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/connect/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/abilityai/abilities/connect"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/connect.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 | $0.00038 | $0.03155 |
| Opus 5.5 | $0.00015 | $0.01262 |
| Sonnet 5.5 | $0.00008 | $0.00631 |
| Haiku 4.5 | $0.00004 | $0.00315 |
Grade B, and why
connect scanned grade B 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 16d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 700 ~/.trinity Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Test connection: `curl -s -o /dev/null -w "%{http_code}" -H "Authorization: Bearer {token}" {instance_url}/api/users/me` How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/trinity:connect
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.connect vX.Y — recent: <summary>. Then proceed.
Connect to a Trinity instance and configure MCP server. No CLI installation required.
Trigger
User wants to:
- Connect to Trinity for the first time
- Set up Trinity MCP integration
- Authenticate with a Trinity instance
- "connect to trinity", "trinity login", "set up trinity"
Flow
PHASE 0: Check Existing Connection
Check if already connected:
cat ~/.trinity/config.json 2>/dev/null | jq -r '.current_profile // empty'
If a profile exists, check if it's still valid:
- Read the current profile's instance_url and token
- Test connection:
curl -s -o /dev/null -w "%{http_code}" -H "Authorization: Bearer {token}" {instance_url}/api/users/me - If 200 (profile valid): ensure
.mcp.jsonin the current directory is present and correct before reporting done./trinity:connectis the single writer of.mcp.json—/trinity:onboard,/trinity:sync, and/trinity:loopdelegate here rather than writing it themselves, so a valid profile must still (re)materialize the file for the current agent directory:- Derive the MCP URL and write the
trinityserver block from the stored profile'sinstance_url+mcp_api_key, exactly as in PHASE 6 — no email round-trip needed. If the file was already present and identical, leave it. - Report: "Already connected to {instance_url}.
.mcp.json[written / refreshed / already current]. Reconnect with/mcpif it just changed. Run/trinity:connect --forceto re-authenticate or switch instances." Then skip to PHASE 7 (verify) — do not re-run the email flow.
- Derive the MCP URL and write the
- If not 200: Continue with flow (token expired)
PHASE 1: Get Instance URL
Ask: "What's your Trinity instance URL?"
Examples (Trinity is self-hosted — every instance is one the user or their team runs):
https://trinity.yourcompany.com(a server behind HTTPS)https://<droplet-ip>(the DigitalOcean guided installer — Caddy terminates HTTPS on the Droplet's IP)http://<server-ip>(a self-hosted remote server — add:PORTif the frontend was moved off 80)http://localhost(local Docker on this machine)
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.
- 16d ago Changed · +1 lines b0b5d8889e7e
- 28d ago Changed · +2 lines 34e59841f7a7
- 29d ago Changed · +1 lines 022ce90c2a17
- 1mo ago Changed · +14 lines b416f6758aed
- 1mo ago First seen · 250 lines · 38 tokens per session scan B cd656f23382c
connect is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 3,155 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".