add-connector

add-connector is a skill for Claude Code from sliamh11/Deus. It costs 49 tokens per session (7,670 once invoked), scanned A, original, MIT.

A connector setup for routing Claude Code sessions to other language-model services, such as GPT through CLIProxyAPI or a local Ollama installation. It keeps the surrounding session features while changing which model receives requests.

In plain words
What is it for?
It helps configure and launch `deus connect` sessions through registered connectors, including CLIProxyAPI and Ollama.
Why use it?
It avoids treating model routing as a separate kind of session, so identity, saved context, preferences, and portable skills can continue to work together.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/connectors_cli.py list.

Good fit It helps configure and launch deus connect sessions through registered connectors, including CLIProxyAPI and Ollama.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus
agentmods
npx agentmods add skills/sliamh11/deus/add-connector

Made for: Claude Code.

Wrote 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.

agentmods badge for add-connector

README.md
[![agentmods](https://agentmods.dev/badge/skills/sliamh11/deus/add-connector.svg)](https://agentmods.dev/skills/sliamh11/deus/add-connector)
Your own site
<a href="https://agentmods.dev/skills/sliamh11/deus/add-connector"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/add-connector.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,670 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 14 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 608
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 612
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 625
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Rogue Agent · line 242
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 367
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 368
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 376
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 396
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 487
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 607
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 608
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 376
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 396
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 570
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.07670
Opus 5 $0.00024 $0.03835
Sonnet 5 $0.00010 $0.01534
Haiku 4.5 $0.00005 $0.00767

Measured 8d ago against content hash 2c3ac031d787, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

add-connector scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:11434/api/version
.claude/skills/add-connector/SKILL.md · 630 lines

How it starts

The opening of the file, as written. The whole thing — 630 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a deus connect Connector

deus connect launches the real, unmodified claude binary with which upstream model answers its requests redirected via ANTHROPIC_BASE_URL — identity, vault/memory context, preferences, and portable skills stay intact, exactly like a normal deus/deus home session. This is separate from Deus's own container-agent backend adapters (deus codex, DEUS_AGENT_BACKEND) — see docs/decisions/backend-neutral-agent-runtime.md's note near the Parity Matrix.

This skill is generic over any registered connector (ships with cliproxy-oauth and ollama) — adding another connector in the future changes connectors/providers/, not this skill.

Four distinct "ollama" surfaces exist in this repo — do not conflate them when guiding a user:

  1. deus connect ollama (this skill, this section) — routes a Claude Code session directly to a local Ollama instance via its native Anthropic-API mode. No proxy, no daemon management.
  2. deus provider ollama / deus fcc (deus-cmd.sh's fcc proxy system) — a different mechanism: routes through fcc-server's OpenAI-compat translation proxy. Also reaches a local Ollama install, but via proxy translation, not a direct native-mode redirect.
  3. deus backend set ollama — a persisted DEUS_AGENT_BACKEND value. Not yet wired to a working CLI agent; its stub error message points here (deus connect ollama) and to deus provider ollama/fcc.
  4. .claude/skills/add-ollama-tool — an unrelated feature: adds an Ollama MCP server so a container agent (not a deus connect session) can offload tasks to a local model.

Phase 1: Pre-flight

python3 scripts/connectors_cli.py list

Shows every registered connector and whether it's already configured. If the target connector shows configured (e.g. a repeat run, or a machine inherited from another user), still walk through Phase 2 (select) and Phase 3 (risk acknowledgment) — Phase 3 is required every time, regardless of configuration state, per its own rule; skipping it here would let an already-configured install proceed straight to a real connector launch without ever showing the risks. Only Phases 4-8 (install/authenticate/ write-config) are skippable on an already-configured connector — jump from Phase 3 straight to Phase 9 (Verify) unless the user explicitly wants to reconfigure.

Read the full file on GitHub · 630 lines

Changes

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.

  1. 8d ago First seen · 630 lines · 49 tokens per session scan A 2c3ac031d787

Subscribe to this mod's changes

add-connector is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 7,670 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.