workflow

A command for launching a custom team workflow using a user-defined mode. It reads the workflow instructions, asks for the desired outcomes, invokes the selected mode, and applies that mode throughout the run.

In plain words
What is it for?
Use it to start a custom multi-step workflow with fixed mode instructions and user-provided context.
Why use it?
It keeps a workflow tied to the mode supplied by the user and defines what happens if someone tries to change that mode partway through.

Command

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 commands/dheerg/swarms/workflow
Clone the repo
git clone --depth 1 https://github.com/DheerG/swarms
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 768 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00010 $0.00768
Opus 5 $0.00005 $0.00384
Sonnet 5 $0.00002 $0.00154
Haiku 4.5 $0.00001 $0.00077

Measured yesterday against content hash b87a75ca5f78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

workflow scanned grade B with 1 finding 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 yesterday.

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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

If the Skill tool cannot find the mode skill, tell the user: "Mode skill '[name]' not found. Verify that `.claude/skills/[name]/SKILL.md` exists in your project." Stop and wait.
commands/workflow.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/swarm:workflow

Read ${CLAUDE_PLUGIN_ROOT}/commands/launch.md and execute it in full — every step, in order — with these overrides:

  • Mode: the custom mode skill parsed below, fixed. Skip mode inference and mode selection entirely; never ask about mode. If the user asks to change the mode at the Step 7 gate, say the mode is fixed for this run and point them to /swarm:workflow <other-mode> (or a built-in shortcut / /swarm:launch for built-in modes) — do not switch modes mid-command.
  • Mode skill invocation: invoke the mode skill here, before the outcomes flow (see "Mode Skill Invocation" below). At launch.md Step 8b it is already invoked — apply its spec directly, do not re-invoke.
  • Outcomes question (Step 2): the mode skill's Outcomes Question (or its base's, for extensions) if it defines one; otherwise "What outcomes do you want the team to achieve? (Describe what should be different or better when the work is done.)"
  • Suggest-members: when invoking swarm:suggest-members, pass the mode skill's Suggest-Members Guidance (for extensions: the base's guidance plus the supplement) along with the confirmed outcomes.
  • User-Provided Context: everything after the mode-skill name in the arguments below stands in for launch.md's $ARGUMENTS — launch.md's own context section is unsubstituted when read from disk.

No lead research unless enabled. Unless the user explicitly enables lead research, do not read codebase files, spawn subagents, or perform research. Delegate all research to teammates.

Parsing $ARGUMENTS

$ARGUMENTS

The first word of $ARGUMENTS is the mode skill name (e.g., blog-mode). Everything after it is the user-provided context. If $ARGUMENTS is empty, ask the user: "Which custom mode skill should I use?" (plain text, not AskUserQuestion). Wait for their response.

Mode Skill Invocation

Invoke the mode skill by its unqualified name via the Skill tool (e.g., blog-mode, not swarm:blog-mode) before the outcomes flow. User-defined mode skills live in the project's .claude/skills/ directory and are resolved without namespace prefix.

Read the full file on GitHub · 34 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. yesterday First seen · 34 lines · 10 tokens per session scan B b87a75ca5f78

Subscribe to this mod's changes

workflow is a command published in the GitHub repository DheerG/swarms (86 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 768 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.