claude-code-session-broker

claude-code-session-broker is a skill for Claude Code from Arch1eSUN/Arcgentic. It costs 35 tokens per session (3,405 once invoked), scanned A, original, MIT.

A coordination layer for running Arcgentic V2 in Claude Code, an AI coding environment. It connects fixed Planner, Developer, and Auditor sessions through a broker.

In plain words
What is it for?
Use it to dispatch work between the five defined Arcgentic roles using Claude Code subagents, hooks, or explicit result handoff.
Why use it?
It keeps the required role assignments and shared state consistent even though Claude Code provides different ways for agents to communicate.

Skill for Claude Code

Written for Claude Code: SubagentStop hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the arcgentic plugin — 18 skills, 9 agents, 1 MCP server shipped together

Good fit Use it to dispatch work between the five defined Arcgentic roles using Claude Code subagents, hooks, or explicit result handoff.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arch1esun/arcgentic/claude-code-session-broker
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 Arch1eSUN/Arcgentic --skill claude-code-session-broker
Clone the repo
git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic

Made for: Claude Code.

Or install arcgentic, the plugin that ships this one along with the rest of its 18 skills, 9 agents, 1 MCP server.

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-code-session-broker

README.md
[![agentmods](https://agentmods.dev/badge/skills/arch1esun/arcgentic/claude-code-session-broker.svg)](https://agentmods.dev/skills/arch1esun/arcgentic/claude-code-session-broker)
Your own site
<a href="https://agentmods.dev/skills/arch1esun/arcgentic/claude-code-session-broker"><img src="https://agentmods.dev/badge/skills/arch1esun/arcgentic/claude-code-session-broker.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,405 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: 1 finding, 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 Data Exfiltration · line 144
    Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
    Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 $0.00035 $0.03405
Opus 5 $0.00017 $0.01702
Sonnet 5 $0.00007 $0.00681
Haiku 4.5 $0.00003 $0.00341

Measured 8d ago against content hash 66542e9ce9fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-code-session-broker 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.

skills/claude-code-session-broker/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-code-session-broker

Use this skill for Claude Code V2 parity. Claude Code does not expose the same Codex thread tools to Arcgentic, so V2 parity is broker-backed: the broker keeps the same four-role state contract and uses native Claude Code tooling (subagents via Agent/SendMessage/ListAgents), hooks, or explicit copy-back, depending on what the host supports — see "Broker priority" below for the exact three transports and their order.

Relevant host capabilities:

Contract

V2 still has exactly five role identities:

  • Orchestrator
  • Planner
  • Developer
  • Test
  • Auditor

Do not create round-numbered role identities. Store round identity in state and prompt payloads.

Broker priority

Use the strongest available transport, checked in this order:

  1. Native tooling (tier 0) — if this session's own tool list includes Agent, SendMessage, and ListAgents, use them directly (see "Procedure — tier 0" below). For a first-time dispatch to a role (kind: "create"), dispatch is synchronous for a foreground Agent call (you get the role's output the moment the call returns — no external event to wait for) or notification-driven for a background Agent call (a task-notification arrives with the role's output when it finishes); either way, Agent's result carries a resumable agentId you record as the broker thread-id. For a repeat dispatch to a role that already has a recorded thread (kind: "reuse" — e.g. a needs_fix loop back to Developer), skip Agent entirely and use SendMessage against that already-recorded agentId instead; its reply arrives asynchronously, like a background Agent call's notification.
  2. Hook-backed broker (fallback) — use when tier 0's three tools are not present in this session (see "Procedure — hook fallback" below).
  3. Explicit copy-back (last resort) — when neither of the above is available: the role session returns RoleReturnSignal in its own output, and a human or the orchestrator manually runs arcgentic v2-return-signal with that JSON. No automation attempts this on its own; do not pretend it succeeded silently.

Read the full file on GitHub · 315 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 · 315 lines · 35 tokens per session scan A 66542e9ce9fe

Subscribe to this mod's changes

claude-code-session-broker is a skill published in the GitHub repository Arch1eSUN/Arcgentic (292 stars, last pushed 26d ago), licensed MIT. It adds 35 tokens to every session and 3,405 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 2026-08-30.

Related

Other skills, from other repositories

debt-ops-init

Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…

bcanfield/agentic-tech-debt · 76 tokens

debt-ops-add

Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…

bcanfield/agentic-tech-debt · 115 tokens

debt-ops-metrics

Print a debt-ops health summary from the metrics log, covering registration rate, feedback action rate, ADR creation, and AI-authored share. Use when the user asks for "debt-ops metrics", "debt health", "registry stats", or a tech-debt health summary. Read-only, never writes the log.

bcanfield/agentic-tech-debt · 74 tokens

debt-ops-review

Audit the tech-debt registry, rank survivors by churn × Fowler quadrant, surface a top-N list, then walk paydown on user follow-up. Use when the user asks to review debt, see what to pay down, work through entries, or check the debt registry. Stale entries drop with "drop A,B,C".

bcanfield/agentic-tech-debt · 72 tokens

repo-hygiene

Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.

QwenLM/qwen-code · 48 tokens

find-simplifications

Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…

QwenLM/qwen-code · 103 tokens