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.
npx agentmods add commands/dheerg/swarms/workflowgit clone --depth 1 https://github.com/DheerG/swarmsWhat 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 | $0.00010 | $0.00768 |
| Opus 5 | $0.00005 | $0.00384 |
| Sonnet 5 | $0.00002 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
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. 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:launchfor 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.
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.
- yesterday First seen · 34 lines · 10 tokens per session scan B b87a75ca5f78
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.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
full
Run the full hope pipeline — intent, shape, target, freeze as needed — then execute.
token-review
Analyze SDLC token usage from .claude/sdlc/token-log.json (last run) and token-history.jsonl (rolling). Surfaces the biggest cost centers and concrete optimization candidates. Read-only.
start
Activate the SDLC workflow (opt-in), re-enable after suspension, or start a new task when already enabled. On fresh install — auto-detects repo/CI/stack/tracker (≤3 prompts), creates .enabled, takes a one-sentence task description, and auto-generates scope.md and a draft plan. On re-enable — verifies the suspension…
build
Start Phase 4 — implement the approved design with surgical-edit discipline and work-item traceability.
configure
Guided setup for config/tools.json and config/tools.local.json. Replaces manual file editing for first-time setup and common reconfigurations. Auto-invoked on fresh install (Layer 0) and when a command finds its required config missing (Layer 2). Safe to run anytime for proactive changes.