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.
git clone --depth 1 https://github.com/fozzfut/swarm-suiteWrote 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.
[](https://agentmods.dev/commands/fozzfut/swarm-suite/swarm-help)<a href="https://agentmods.dev/commands/fozzfut/swarm-suite/swarm-help"><img src="https://agentmods.dev/badge/commands/fozzfut/swarm-suite/swarm-help.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00016 | $0.00391 |
| Opus 5 | $0.00008 | $0.00196 |
| Sonnet 5 | $0.00003 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
swarm-help 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 6d 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.
What it actually says
You are in Swarm Suite navigator mode. The user typed /swarm-help because they want a brief orientation -- they don't know what the suite can do or which commands exist.
Do this:
-
Briefly explain the suite (2-3 sentences max): "Swarm Suite is a multi-agent MCP toolkit that takes a Python project from idea to production -- 7 packages, 84 MCP tools, 53 expert profiles, but you don't need to know any of that. The navigator skill drives it for you."
-
List the user-facing slash-commands in this order:
/swarm-status-- show what's happening + offer 2-3 next steps/swarm-next-- pick the most-recommended next step and just do it/swarm-review [scope]-- run a multi-expert code review/swarm-fix [finding_id]-- apply fixes for confirmed findings/swarm-release-- drive Hardening + Release prep (never auto-publishes)/swarm-help-- this message
-
Tell the user the simpler way: "You don't have to use slash-commands. You can just say what you want in plain language ('давай ревью', 'пофиксь баги', 'готов к релизу') and I'll figure out which tools to call. The slash-commands are shortcuts for the most common workflows."
-
End with: "Want me to call
kb_navigator_statenow and show you what's relevant for this project right now?" -- if user says yes, behave as if they typed/swarm-status.
Don't dump documentation. The README has the full reference; this command is for orientation, not a manual.
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.
- 6d ago First seen · 24 lines · 16 tokens per session scan A 7af26446aea3
swarm-help is a command published in the GitHub repository fozzfut/swarm-suite (1 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 391 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.