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 Arch1eSUN/Arcgentic --skill claude-code-session-brokergit clone --depth 1 https://github.com/Arch1eSUN/ArcgenticWrote 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/arch1esun/arcgentic/claude-code-session-broker)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00035 | $0.03405 |
| Opus 5 | $0.00017 | $0.01702 |
| Sonnet 5 | $0.00007 | $0.00681 |
| Haiku 4.5 | $0.00003 | $0.00341 |
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.
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:
- Subagents provide isolated role contexts within a session, and back
tier 0's
Agent/SendMessage/ListAgentsdispatch: https://code.claude.com/docs/en/sub-agents - Hooks can observe stop events and final assistant output, and back the hook-backed broker fallback: https://code.claude.com/docs/en/hooks
- Agent Teams (https://code.claude.com/docs/en/agent-teams) coordinate across separate sessions when enabled, but they are a different host feature from this skill's three transports below. Tier 0 supersedes Agent Teams for V2 dispatch — do not treat Agent Teams as a live, separate transport option here.
Contract
V2 still has exactly five role identities:
OrchestratorPlannerDeveloperTestAuditor
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:
- Native tooling (tier 0) — if this session's own tool list includes
Agent,SendMessage, andListAgents, use them directly (see "Procedure — tier 0" below). For a first-time dispatch to a role (kind: "create"), dispatch is synchronous for a foregroundAgentcall (you get the role's output the moment the call returns — no external event to wait for) or notification-driven for a backgroundAgentcall (a task-notification arrives with the role's output when it finishes); either way,Agent's result carries a resumableagentIdyou record as the brokerthread-id. For a repeat dispatch to a role that already has a recorded thread (kind: "reuse"— e.g. aneeds_fixloop back to Developer), skipAgententirely and useSendMessageagainst that already-recordedagentIdinstead; its reply arrives asynchronously, like a backgroundAgentcall's notification. - Hook-backed broker (fallback) — use when tier 0's three tools are not present in this session (see "Procedure — hook fallback" below).
- Explicit copy-back (last resort) — when neither of the above is
available: the role session returns
RoleReturnSignalin its own output, and a human or the orchestrator manually runsarcgentic v2-return-signalwith that JSON. No automation attempts this on its own; do not pretend it succeeded silently.
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.
- 8d ago First seen · 315 lines · 35 tokens per session scan A 66542e9ce9fe
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.
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…
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…
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.
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".
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.
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…