update-workflow

A command that refreshes the shortcut wiring for an existing custom workflow using the current Swarm template.

In plain words
What is it for?
Use it when an existing workflow’s command file needs to match a newer Swarm template. It checks that the workflow exists and updates only its Swarm-owned sections.
Why use it?
It keeps the workflow command up to date without overwriting the workflow’s separately owned mode instructions.

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/update-workflow
Clone the repo
git clone --depth 1 https://github.com/DheerG/swarms
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,327 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 $0.00015 $0.02327
Opus 5 $0.00008 $0.01163
Sonnet 5 $0.00003 $0.00465
Haiku 4.5 $0.00002 $0.00233

Measured yesterday against content hash 5da735fdcb7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-workflow 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 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.

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.

commands/update-workflow.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/swarm:update-workflow

You are updating an existing custom workflow's shortcut command to match the current swarm template. This command regenerates only the plugin-owned wiring of .claude/commands/<name>.md — the ## Workflow section and default wiring that comes from swarm. It never touches the mode skill at .claude/skills/<name>-mode/SKILL.md — that file is consumer-owned.

Step 0: Parse argument

$ARGUMENTS

The argument is the workflow name (kebab-case, matching the existing file name without .md). If $ARGUMENTS is empty, ask the user (plain text, not AskUserQuestion): "Which workflow should I update? (Pass the name — e.g., triage-gh-issue.)" Wait for their response.

Step 1: Locate and read the existing file

The target file is .claude/commands/<name>.md in the current working directory.

  • If the file does not exist: tell the user "No workflow found at .claude/commands/<name>.md. This command updates existing workflows — use /swarm:create-workflow to create a new one." Stop.
  • If the file exists: use the Read tool to read it.

Do not read or modify .claude/skills/<name>-mode/SKILL.md. That file is consumer-owned.

Step 2: Extract consumer-owned sections

From the existing shortcut command, extract these consumer-owned values and blocks verbatim. These will be preserved:

  • Frontmatter fields: description, argument-hint, disable-model-invocation, and any other fields present. Preserve all of them.
  • ## Settings section — the entire block under the ## Settings heading, including Mode, Outcomes question, Defaults, and any other settings the consumer has added.
  • ## User-Provided Context section — the block under that heading (typically $ARGUMENTS).
  • ## Pre-flight section if present — the block under that heading (intake-specific actions, bash commands, arg parsing). This is consumer-owned.
  • Any section not recognized as plugin-owned — preserve as-is.

Consumer ownership rule: anything that is not the plugin-owned wiring (the template preamble and the ## Workflow section) belongs to the consumer.

Read the full file on GitHub · 119 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 · 119 lines · 15 tokens per session scan A 5da735fdcb7e

Subscribe to this mod's changes

update-workflow is a command published in the GitHub repository DheerG/swarms (86 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 2,327 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.