Agent Management

Agent Management is a skill for Claude Code from sseshachala/conductai. It costs 14 tokens per session (1,691 once invoked), scanned A, original, Apache-2.0.

A skill for managing coding-agent agents: creating, editing, upgrading, deleting, and auditing them. Agents are specialized configurations that give an AI worker a defined role and instructions.

In plain words
What is it for?
It is for creating or maintaining specialist and orchestrator agents, reviewing their configuration, and managing files in `.claude/agents/`.
Why use it?
It provides a documented process for changing agents while keeping their names, roles, files, and required approval steps consistent.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the conductai plugin — 3 skills, 5 agents, 5 hooks, 1 MCP server, 2 plugins shipped together

Good fit It is for creating or maintaining specialist and orchestrator agents, reviewing their configuration, and managing files in .claude/agents/.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sseshachala/conductai/rundock-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 sseshachala/conductai --skill rundock-agents
Clone the repo
git clone --depth 1 https://github.com/sseshachala/conductai

Made for: Claude Code.

Or install conductai, the plugin that ships this one along with the rest of its 3 skills, 5 agents, 5 hooks, 1 MCP server, 2 plugins.

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 Agent Management

README.md
[![agentmods](https://agentmods.dev/badge/skills/sseshachala/conductai/rundock-agents.svg)](https://agentmods.dev/skills/sseshachala/conductai/rundock-agents)
Your own site
<a href="https://agentmods.dev/skills/sseshachala/conductai/rundock-agents"><img src="https://agentmods.dev/badge/skills/sseshachala/conductai/rundock-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,691 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 Prompt Injection · line 61
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable 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 $0.00014 $0.01691
Opus 5 $0.00007 $0.00846
Sonnet 5 $0.00003 $0.00338
Haiku 4.5 $0.00001 $0.00169

Measured 8d ago against content hash 97a3b12ddfb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Agent Management 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/rundock-agents/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manage agents in .claude/agents/. This skill covers the full lifecycle.

Important: file access

Claude Code blocks Write and Edit tools for files inside .claude/. Do NOT use Write, Edit, or Bash to create, modify, or delete agent files. Instead, use RUNDOCK markers. The Rundock client detects these markers in your response and saves the files through the server.

Create an agent

1. Gather details

Ask the user:

  • What should this agent do? (responsibilities, domain)
  • What should it be called? (suggest a slug name and display name)
  • What type is it? (orchestrator or specialist)

If the user already provided enough detail, skip straight to drafting.

2. Choose identity

Naming convention: The name (slug), filename, and role must all refer to the same thing. The slug is the hyphenated lowercase form of the role. Examples: role "Content Lead" = slug content-lead, role "Executive Assistant" = slug executive-assistant, role "Design Lead" = slug design-lead. The displayName is a separate, short human name unrelated to the role (e.g. "Penn", "Lea", "Des"). Never use the displayName as the slug.

Suggest and confirm:

  • name (slug): Hyphenated lowercase form of the role. This becomes both the name field and the filename ({slug}.md). Must describe the role, not the person.
  • displayName: Short, memorable, character-style name. Good: "Dex", "Intel", "Kit". Bad: "Meetings Agent", "Project Tracker". Must not match or resemble the slug. The role field carries the functional title.
  • role: 2-4 word title (e.g. "Meeting Intelligence", "Content Strategist"). The slug is derived from this.
  • icon: Single unicode character. Must be visually distinct from existing agents.
  • colour: Hex colour for avatar. Must be visually distinct from existing agents.
  • order: 0 for orchestrator, sequential integers for specialists. Use decimals for sub-agents (e.g. 1.1, 1.2 under a lead at order 1). Check existing agents to avoid collisions.
  • reportsTo: The name slug of the agent this one reports to. Every specialist should have this set. Direct reports of the orchestrator use the orchestrator's slug. Sub-agents use their lead's slug.
  • model: opus for orchestrator, sonnet for most specialists

Read the full file on GitHub · 158 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 · 158 lines · 14 tokens per session scan A 97a3b12ddfb1

Subscribe to this mod's changes

Agent Management is a skill published in the GitHub repository sseshachala/conductai (32 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 1,691 once invoked, about $0.0001 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

background-task

Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.

vstorm-co/full-stack-ai-agent-template · 62 tokens

agent-tool

Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.aiframework }}.

vstorm-co/full-stack-ai-agent-template · 66 tokens

frontend-feature

Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.

vstorm-co/full-stack-ai-agent-template · 64 tokens

rag-knowledge

Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…

vstorm-co/full-stack-ai-agent-template · 76 tokens

alembic-migration

Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.

vstorm-co/full-stack-ai-agent-template · 56 tokens

channel-bot

Work with messaging-channel bots (Telegram / Slack) — register a bot, route inbound messages through the AI agent, handle webhooks vs polling, or add a new channel adapter. Use when wiring chat into a messaging platform or debugging bot delivery.

vstorm-co/full-stack-ai-agent-template · 53 tokens