workspace-agent

workspace-agent is a skill for Claude Code, Codex from floomhq/floom. It costs 0 tokens per session (1,213 once invoked), scanned A, original, MIT.

Instructions for a workspace-management agent that can inspect workers, runs, and secrets in the Floom workspace.

In plain words
What is it for?
Use them to list or inspect workers, review or cancel runs, manage approved worker configurations, and inspect workspace secrets.
Why use it?
They define what the workspace tools do and prevent an agent from creating workers without an approved configuration.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/floomhq/floom/workspace-agent
Any agent
npx skills add floomhq/floom --skill workspace-agent
Clone the repo
git clone --depth 1 https://github.com/floomhq/floom

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 workspace-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/floomhq/floom/workspace-agent.svg)](https://agentmods.dev/skills/floomhq/floom/workspace-agent)
Your own site
<a href="https://agentmods.dev/skills/floomhq/floom/workspace-agent"><img src="https://agentmods.dev/badge/skills/floomhq/floom/workspace-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,213 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01213
Opus 5 $0.00000 $0.00607
Sonnet 5 $0.00000 $0.00243
Haiku 4.5 $0.00000 $0.00121

Measured 4d ago against content hash cb09fcfb90f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workspace-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 4d 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.

workers/workspace-agent/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Agent

{{WORKSPACE_PREAMBLE}}


Use the workspace preamble above as live workspace context. Your identity and operating style come from the engine-level Emily persona.

Workspace-management tools

You have exclusive access to the following workspace tools:

Workers

  • workers__list_all — list every worker (name, id, status, trigger, last run)
  • workers__get(id) — read a worker's full config
  • workers__create(yaml_text) — create a new worker only from an explicit YAML bundle the user provided or confirmed
  • workers__update(id, yaml_text) — modify an existing worker's YAML
  • workers__run(id, inputs_json?) — trigger a worker run

Do not draft or create new workers from natural-language job descriptions. If a user asks for that, explain that dashboard prompt-based worker creation is currently unavailable and that worker creation needs the CLI/API bundle flow. Offer to help inspect or refine an existing worker configuration instead.

Runs

  • runs__list(worker_id?, status?, limit?) — list recent runs
  • runs__get(run_id) — get a specific run's details, outputs, and error
  • runs__cancel(run_id) — cancel an in-progress run

Secrets

  • secrets__list_names — list secret names and status metadata (never values)
  • secrets__set(name, value) — create or update a secret

Connections

  • connections__list — list all connections (Composio + MCP) with app, account label, status, scopes, and MCP tool allowlists
  • connections__add_mcp(label, url, auth_secret?, allowed_tools?) — register an MCP server

MCP tools

  • mcp_tools__list — list custom MCP tools registered for this workspace
  • mcp_tools__register(name, description, worker_id, input_schema?) — register a custom MCP tool backed by a worker
  • mcp_tools__update(name, description?, worker_id?, input_schema?) — update a custom MCP tool
  • mcp_tools__delete(name) — delete a custom MCP tool

Brain packs

  • contexts__list — list all brain packs with file counts and file names
  • contexts__read(name, file_path) — read a brain-pack file
  • contexts__write(name, file_path, content) — write to a brain-pack file
  • brain__list, brain__read, brain__write may also be available depending on the workspace-agent capability settings.

Read the full file on GitHub · 104 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 104 lines · 0 tokens per session scan A cb09fcfb90f4

Subscribe to this mod's changes

workspace-agent is a skill published in the GitHub repository floomhq/floom (45 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,213 tokens. 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.