claude-managed-agents

claude-managed-agents is a skill for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 45 tokens per session (3,384 once invoked), scanned A, original, Apache-2.0.

A reference for connecting an application to Claude Managed Agents, Anthropic's hosted service for running AI agents with tools, sandboxed environments, and saved session state. It focuses on the service's API and security patterns.

In plain words
What is it for?
Use it when integrating hosted Claude agents, asynchronous sessions, reverse-tunnel tools, or server-side agent state into an application.
Why use it?
It removes the need to build your own long-running agent loop, tool connection, sandbox handling, and session persistence.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions Claude Code.

Good fit Use it when integrating hosted Claude agents, asynchronous sessions, reverse-tunnel tools, or server-side agent state into an application.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terrene-foundation/kailash-coc-claude-py/36-claude-managed-agents
Install

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.

Any agent
npx skills add terrene-foundation/kailash-coc-claude-py --skill 36-claude-managed-agents
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-py

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 claude-managed-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/36-claude-managed-agents/github.svg)](https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/36-claude-managed-agents)
Your own site
<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/36-claude-managed-agents"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/36-claude-managed-agents/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.

agentmods 80×15 button for claude-managed-agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/36-claude-managed-agents"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/36-claude-managed-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,384 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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: 12 findings, up to medium

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 →

  • medium Prompt Injection · line 27
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 181
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 183
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 184
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 185
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 187
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 188
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 189
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 190
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 191
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 213
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 222
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 $0.00045 $0.03384
Opus 5 $0.00023 $0.01692
Sonnet 5 $0.00009 $0.00677
Haiku 4.5 $0.00005 $0.00338

Measured 8d ago against content hash 38a3ed75871b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

claude-managed-agents 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 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.

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.

.claude/skills/36-claude-managed-agents/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Managed Agents — Integration Patterns

Claude Managed Agents (CMA) is Anthropic's hosted REST agent harness (/v1/agents, /v1/environments, /v1/sessions; beta header managed-agents-2026-04-01). It bundles the agent loop + tool execution + sandbox container + server-side state persistence so you do not build your own loop. Use it for long-running / async work; use the Messages API when you want a custom loop.

Not Claude Code. CMA is the Claude API product. Claude Code is the CLI/IDE coding agent. They share the model + tool-use vocabulary but are distinct products — do not conflate them in code, docs, or consumer guidance.

Kailash relationship. CMA is NOT a Kailash framework. For agent work INSIDE a Kailash app, the framework binding is Kaizen (rules/framework-first.md). This skill is for the case where a Kailash-app builder integrates the hosted CMA harness as an external service — the wire protocol + its security hardening. When the question is "build an agent," default to Kaizen first.

Core model (four concepts)

Concept What it is
Agent model + system + tools + mcp_servers + skills. Versioned. POST /v1/agents — created ONCE, referenced by ID across sessions.
Environment Where sessions run: Anthropic cloud sandbox, or self-hosted sandbox on your infra (POST /v1/environments).
Session A running agent instance for one task. POST /v1/sessions references an agent by ID/version. Created PER RUN.
Events The only communication channel. You send user.*/system.*; you receive agent.*/session.*/span.*.

Read the full file on GitHub · 237 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 · 237 lines · 45 tokens per session scan A 38a3ed75871b

Subscribe to this mod's changes

claude-managed-agents is a skill published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 24d ago), licensed Apache-2.0. It adds 45 tokens to every session and 3,384 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 2026-09-03.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

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".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

aws-sdk-java-v2-core

Provides AWS SDK for Java 2.x client configuration, credential resolution, HTTP client tuning, timeout, retry, and testing patterns. Use when creating or hardening AWS service clients, wiring Spring Boot beans, debugging auth or region issues, or choosing sync vs async SDK usage.

giuseppe-trisciuoglio/developer-kit · 62 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens