remove-agent

remove-agent is a skill for Claude Code from golemfoundation/octant-council-builder. It costs 7 tokens per session (922 once invoked), scanned A, original, MIT.

An agent-removal tool for an evaluation council, which is a group of automated agents that assess a project. It removes the selected agent’s definition and documentation, then updates the council plan when one exists.

In plain words
What is it for?
Use it to remove a named council agent or choose one from a roster grouped by data gathering, evaluation, and synthesis roles. It is intended for changing which agents participate in the council.
Why use it?
It avoids manually finding related files and keeping the council plan in sync. It also checks the available agents before asking which one to remove when no name is supplied.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the council plugin — 11 skills, 10 agents shipped together

Good fit Use it to remove a named council agent or choose one from a roster grouped by data gathering, evaluation, and synthesis roles. It is intended for changing which agents participate in the council.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/golemfoundation/octant-council-builder/remove-agent
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 golemfoundation/octant-council-builder --skill remove-agent
Clone the repo
git clone --depth 1 https://github.com/golemfoundation/octant-council-builder

Made for: Claude Code.

Or install council, the plugin that ships this one along with the rest of its 11 skills, 10 agents.

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 remove-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/remove-agent/github.svg)](https://agentmods.dev/skills/golemfoundation/octant-council-builder/remove-agent)
Your own site
<a href="https://agentmods.dev/skills/golemfoundation/octant-council-builder/remove-agent"><img src="https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/remove-agent/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 remove-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/golemfoundation/octant-council-builder/remove-agent"><img src="https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/remove-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 922 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.
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 $0.00007 $0.00922
Opus 5 $0.00003 $0.00461
Sonnet 5 $0.00001 $0.00184
Haiku 4.5 $0.00001 $0.00092

Measured 10d ago against content hash 694550593112, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

remove-agent 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 10d 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/remove-agent/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remove Council Agent

Remove an agent from the evaluation council. Deletes the agent definition, its documentation, and updates the council plan if one exists.

Step 1: Discover Roster

Glob the agents directory and group by wave:

Glob agents/data-*.md → Wave 1 (Data Gathering)
Glob agents/eval-*.md → Wave 2 (Evaluation)
Glob agents/synth-*.md → Wave 3 (Synthesis)

For each file, read the frontmatter name and description.

If $ARGUMENTS provided

Check if agents/$ARGUMENTS.md exists. If yes, skip to Step 2 with that agent pre-selected. If no, show the roster and ask.

If no argument

Present the roster and ask which agent to remove:

AskUserQuestion:
  question: "Which agent should be removed?"
  header: "Remove Agent"
  options:
    [One option per agent, grouped by wave]:
    - label: "[name]"
      description: "Wave N — [description]"
      preview: |
        File: agents/[name].md
        Wave: [N] — [Data Gathering | Evaluation | Synthesis]
        Role: [description]

        Removing this agent means the council will no longer:
        [1-line summary of what will be lost]

Store the selected agent as $AGENT.

Step 2: Last-Agent Guard

Before confirming, check if this is the last agent of its wave type:

Glob agents/$PREFIX-*.md → count agents of same type

If this is the last synth agent, show a hard warning:

AskUserQuestion:
  question: "This is the only synthesis agent. Removing it means the council will produce NO final report. Continue?"
  header: "Warning"
  options:
    - label: "Remove anyway"
      description: "I'll add a replacement later"
    - label: "Cancel"
      description: "Keep the agent"

If "Cancel" → stop, report "No changes made."

If this is the last data agent or last eval agent, show a softer warning in the confirmation (Step 3) noting that the wave will be empty.

Step 3: Confirm with Impact Preview

Read the agent file to understand its role, then confirm:

AskUserQuestion:
  question: "Confirm removal of $AGENT?"
  header: "Confirm"
  options:
    - label: "Remove"
      description: "Delete agent and documentation"
      preview: |
        Removing: $AGENT
        Wave: [N] — agents remaining: [M-1]

        Impact:
        - The council will no longer assess: [what this agent evaluates/gathers]
        - [Wave-specific impact]:
          - Data agent: evaluators will have less data to work with
          - Eval agent: the synthesis will have fewer perspectives
          - Synth agent: the council output format will change

        Files to delete:
        - agents/$AGENT.md
        - docs/$AGENT.md (if exists)
    - label: "Cancel"
      description: "Keep the agent"

Read the full file on GitHub · 149 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. 10d ago First seen · 149 lines · 7 tokens per session scan A 694550593112

Subscribe to this mod's changes

remove-agent is a skill published in the GitHub repository golemfoundation/octant-council-builder (3 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 922 once invoked, about $0.0000 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 2026-08-31.

Related

Other skills, from other repositories

great_cto

Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.

avelikiy/great_cto · 32 tokens

anti-patterns

Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

avelikiy/great_cto · 59 tokens

cost-model

Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.

avelikiy/great_cto · 59 tokens

migration-ready-schema

Data-model rules that make a schema importable from day one, so the migration-import-engineer is never blocked on missing columns. Every SMB Product-Builder product must let a customer bring their data from an incumbent (ServiceTitan/Toast/Mindbody/Shopify) — that requires provenance (sourceref) and rollback…

avelikiy/great_cto · 133 tokens

stack-baseline

The pinned default technology stack for SMB Product-Builder products. One source of truth so the architect, app-scaffolder, auth-engineer, and senior-dev never re-decide the stack per build — they build ON it. Covers framework, ORM/DB, auth, UI, payments/email/SMS, files, jobs, testing, hosting, and observability…

avelikiy/great_cto · 126 tokens

agent-workflow-playbook

AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…

Gingiris-1031/gingiris-skills · 83 tokens