A command that chooses and runs the highest-priority next action in a Swarm Suite project pipeline.

Continuing unfinished work, advancing the current pipeline stage, and executing the tools required for the selected next step.

It removes the need to inspect the pipeline and decide manually what should happen next, while pausing for confirmation before destructive actions.

swarm-next — Command for Claude Code by fozzfut/swarm-suite

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.

Clone the repo

git clone --depth 1 https://github.com/fozzfut/swarm-suite

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/fozzfut/swarm-suite/swarm-next/github.svg)](https://agentmods.dev/commands/fozzfut/swarm-suite/swarm-next)

Your own site

<a href="https://agentmods.dev/commands/fozzfut/swarm-suite/swarm-next"><img src="https://agentmods.dev/badge/commands/fozzfut/swarm-suite/swarm-next/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/fozzfut/swarm-suite/swarm-next"><img src="https://agentmods.dev/badge/commands/fozzfut/swarm-suite/swarm-next.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 330 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.00330
Opus 5.5	$0.00006	$0.00132
Sonnet 5.5	$0.00003	$0.00066
Haiku 4.5	$0.00002	$0.00033

Measured 2mo ago against content hash 6fa6ab5b914c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swarm-next 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 2mo 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/commands/swarm-next.md · 20 lines

What it actually says

You are in Swarm Suite navigator mode. The user typed /swarm-next because they want you to just do the next sensible step rather than ask them to choose.

Do this:

Call kb_navigator_state(project_path=<cwd>).
Pick the single highest-priority next action from suggested_next_steps. Priority order:
- continue_artifact (anything open and in-flight) wins -- never start something new while a session is mid-flight unless the user explicitly redirects.
- If no in-flight artifact: pick the first stage_continue for the current stage.
- If the stage's main work is done: pick advance (and confirm with user before destructive kb_advance_pipeline).
Tell the user what you're about to do and why (one sentence each).
Confirm with user IF the action is destructive (write to user code, finalise an artifact, advance the pipeline). For all read/scoped tool calls, just do it.
Execute the tool calls from the picked option's tools list, in order, surfacing intermediate results as you go.
After completion, call kb_navigator_state again and tell the user what's next ("done -- next step would be X; want to continue?").

Never ask "which would you like" -- this command means "pick one and run with it." If the user wanted to choose, they'd have used /swarm-status.

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.

2mo ago First seen · 20 lines · 15 tokens per session scan A 6fa6ab5b914c

Subscribe to this mod's changes

swarm-next is a command published in the GitHub repository fozzfut/swarm-suite (1 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 330 once invoked, about $0.0001 per session on Opus 5.5. 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.

Planning

swarm-next next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
swarm-nextfozzfut/swarm-suite	Command	1	6mo ago	MIT	A	15	Claude Code
checklistgithub/spec-kit	Command	148k	today	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	today	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	today	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	today	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	today	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	today	MIT	A	14	Claude Code