agentica-server

agentica-server is a skill for Claude Code from parcadei/Continuous-Claude-v3. It costs 18 tokens per session (1,104 once invoked), scanned A, original, MIT.

A setup and troubleshooting guide for Agentica, a Python system for building AI agents, connected to a local Claude proxy. It explains how the software development kit, server, proxy, and Claude command-line tool communicate.

In plain words
What is it for?
Use it when setting up Agentica locally, starting its server and Claude proxy, configuring endpoint variables, or debugging missing tool access and incorrect agent responses.
Why use it?
It prevents connection mistakes, especially confusing the server's session endpoint with the proxy's inference endpoint. It also provides an order for starting the services and diagnosing failures.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/agentica/claude_proxy.py --port 8080.

not rated 3.9krepo +3 7mo ago A scan Socket: passSnyk: passSkillSpector: warn 18 tokens original MIT

Good fit Use it when setting up Agentica locally, starting its server and Claude proxy, configuring endpoint variables, or debugging missing tool access and incorrect agent responses.

Compare 6 skills from other repositories ↓
About the project

Continuous-Claude-v3 is a Claude Code development environment that preserves working context between sessions, coordinates specialized agents, and stores project knowledge through ledgers, handoffs, and analysis tools. It is for people using Claude Code on ongoing or complex software work. Its catalogue entries are the skills, agents, hooks, plugin, and setting that provide its workflows and orchestration.

parcadei/Continuous-Claude-v3 · 3,936 stars · on GitHub

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/parcadei/Continuous-Claude-v3
agentmods
npx agentmods add skills/parcadei/continuous-claude-v3/agentica-server

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 agentica-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/agentica-server.svg)](https://agentmods.dev/skills/parcadei/continuous-claude-v3/agentica-server)
Your own site
<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/agentica-server"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/agentica-server.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,104 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
  • Socket pass 18 Mar 2026
  • Snyk pass 15 Feb 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 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 Excessive Agency · line 113
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • medium Data Exfiltration · line 149
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00018 $0.01104
Opus 5 $0.00009 $0.00552
Sonnet 5 $0.00004 $0.00221
Haiku 4.5 $0.00002 $0.00110

Measured 9d ago against content hash c99ab347111d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agentica-server 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 9d 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 http://localhost:8080/health
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/agentica-server/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentica Server + Claude Proxy Setup

Complete reference for running Agentica SDK with a local Claude proxy. This enables Python agents to use Claude CLI as their inference backend.

When to Use

Use this skill when:

  • Starting Agentica development with Claude proxy
  • Debugging connection issues between SDK, server, and proxy
  • Setting up a fresh Agentica environment
  • Troubleshooting agent tool access or hallucination issues

Architecture

Agentica SDK (client code)
    | S_M_BASE_URL=http://localhost:2345
    v
ClientSessionManager
    |
    v
Agentica Server (agentica-server)
    | INFERENCE_ENDPOINT_URL=http://localhost:8080/v1/chat/completions
    v
Claude Proxy (claude_proxy.py)
    |
    v
Claude CLI (claude -p)

Environment Variables

Variable Set By Used By Purpose
INFERENCE_ENDPOINT_URL Human agentica-server Where server sends LLM inference requests
S_M_BASE_URL Human Agentica SDK client Where SDK connects to session manager

KEY: These are NOT the same endpoint!

  • SDK connects to server (port 2345)
  • Server connects to proxy (port 8080)

Startup Sequence

Must start in this order (each in a separate terminal):

Terminal 1: Claude Proxy

uv run python scripts/agentica/claude_proxy.py --port 8080

Terminal 2: Agentica Server

MUST run from its directory:

cd workspace/agentica-research/agentica-server
INFERENCE_ENDPOINT_URL=http://localhost:8080/v1/chat/completions uv run agentica-server --port 2345

Terminal 3: Your Agent Script

S_M_BASE_URL=http://localhost:2345 uv run python scripts/agentica/your_script.py

Health Checks

# Claude proxy health
curl http://localhost:8080/health

# Agentica server health
curl http://localhost:2345/health

Common Errors & Fixes

1. APIConnectionError after agent spawn

Symptom: Agent spawns successfully but fails on first call with connection error.

Read the full file on GitHub · 168 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. 9d ago First seen · 168 lines · 18 tokens per session scan A c99ab347111d

Subscribe to this mod's changes

agentica-server is a skill published in the GitHub repository parcadei/Continuous-Claude-v3 (3,936 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 1,104 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

api-design

Use when designing REST endpoints, defining error envelopes, setting a versioning or deprecation policy, choosing pagination shape, adding idempotency to mutations, reviewing API contracts, or when two services need a stable interface between them.

aneja5/forge-skills · 48 tokens

error-handling-and-resilience

Use when establishing error handling patterns for a project, when adding retry logic, circuit breakers, or graceful degradation, when reviewing how a service handles failures, or when an incident reveals that a failure mode was silently swallowed.

aneja5/forge-skills · 50 tokens

fizzy-workflow

Use for guided Fizzy.do workflows: "set up Fizzy", "configure Fizzy for this project", "sync my work to Fizzy", "review my Fizzy progress", "end of session cleanup". Provides step-by-step guidance for common operations.

keskinonur/claude-plugin-fizzy · 57 tokens

event-store

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, implementing event persistence, projections, snapshotting, or CQRS patterns.

wpank/ai · 35 tokens

architecture-patterns

Backend architecture patterns for building maintainable, testable systems: Clean Architecture, Hexagonal Architecture, and Domain-Driven Design.

wpank/ai · 3 tokens

microservices-patterns

Patterns for building distributed systems: service decomposition, inter-service communication, data management, and resilience. Helps you avoid the "distributed monolith" anti-pattern.

wpank/ai · 4 tokens