agent-fleet: Skill for Claude Code

.pi/agent-fleet/hermes/skills/hub-conductor/SKILL.md

hub-conductor is a skill for Claude Code, Codex from chankov/agent-fleet. It costs 35 tokens per session (1,025 once invoked), scanned A, original, MIT.

A conductor skill for coordinating several local coding-agent peers through a command-line messaging bridge. It discovers available peers, delegates bounded tasks, waits for replies, and combines the results.

In plain words
What is it for?
Use it when a request needs parallel research, implementation, documentation, review, testing, follow-up, or result synthesis across local peers.
Why use it?
It organizes parallel specialist work while keeping delegation within the correct project and avoiding uncontrolled fleet or daemon actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is chankov/agent-fleet's own configuration. It tells Claude Code and Codex how to work on agent-fleet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-fleet configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chankov/agent-fleet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chankov/agent-fleet/main/.pi/agent-fleet/hermes/skills/hub-conductor/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chankov/agent-fleet

Made for: Claude Code, Codex.

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 hub-conductor

README.md
[![agentmods](https://agentmods.dev/badge/skills/chankov/agent-fleet/hub-conductor/github.svg)](https://agentmods.dev/skills/chankov/agent-fleet/hub-conductor)
Your own site
<a href="https://agentmods.dev/skills/chankov/agent-fleet/hub-conductor"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/hub-conductor/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 hub-conductor

Your own site · 80×15
<a href="https://agentmods.dev/skills/chankov/agent-fleet/hub-conductor"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/hub-conductor.svg" alt="Reviewed on agentmods" width="80" 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 1,025 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 pass 7 Sept 2026
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 $0.01025
Opus 5.5 $0.00014 $0.00410
Sonnet 5.5 $0.00007 $0.00205
Haiku 4.5 $0.00003 $0.00103

Measured 1mo ago against content hash 3a18b33d5551, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hub-conductor 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 1mo 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.

.pi/agent-fleet/hermes/skills/hub-conductor/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hub Conductor

Overview

You are the human-facing conductor for a local pi coms pool. Your job is to decompose the human's request, discover live hub-team peers, delegate bounded tasks through .pi/agent-fleet/scripts/coms-cli.ts, wait for results, and synthesize a final answer.

This is conductor-side orchestration only: the existing coms CLI is the bridge. You do not need a daemon or standing Hermes peer to ask pi peers for work.

When to Use

Use this skill when:

  • the human asks Hermes to coordinate pi hub-team peers;
  • a task benefits from parallel specialist work such as research, implementation, docs, review, or testing;
  • you need to inspect which local peers are alive before deciding who should do what;
  • a previous peer response needs follow-up, retry, or synthesis.

Do not use it for single-step work Hermes can safely complete alone without peer help.

Process

  1. Identify the repository root and set a shell variable for it when useful:
REPO=/home/nchankov/repos/agent-fleet
  1. Discover live peers in the current coms project:
node --experimental-strip-types "$REPO/scripts/coms-cli.ts" list

Use --project <name> when the human or launch recipe specifies a non-default project.

  1. Choose peers by their listed name and purpose. Send bounded, self-contained prompts that include the expected deliverable and any acceptance assertions the peer must prove.

  2. Delegate with an explicit timeout and wait for the response:

node --experimental-strip-types "$REPO/scripts/coms-cli.ts" send <peer-name> \
  "<bounded task; include required output and evidence>" \
  --await --timeout 300000

Use a longer timeout for build/test/review tasks when needed. Every send --await must include --timeout <ms>.

  1. If a peer times out or is missing, retry at most once when the task still matters. Otherwise report that peer as unavailable and continue with the best available evidence.

  2. Synthesize peer outputs for the human. Name which peers were asked, what each returned, what evidence supports the result, and what remains unproven.

Read the full file on GitHub · 85 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. 1mo ago Changed 3a18b33d5551
  2. 2mo ago First seen · 85 lines · 35 tokens per session scan A c0e2c0e20969

Subscribe to this mod's changes

hub-conductor is a skill published in the GitHub repository chankov/agent-fleet (20 stars, last pushed 12d ago), licensed MIT. It adds 35 tokens to every session and 1,025 once invoked, about $0.0001 per session on Opus 5.5. 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

hub-conductor compared with skills from other repositories

hub-conductor next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hub-conductorchankov/agent-fleetSkill2012d agoMITA35Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code