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/writegit 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 | $0.00006 | $0.00233 |
| Opus 5 | $0.00003 | $0.00117 |
| Sonnet 5 | $0.00001 | $0.00047 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
write 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 2d 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
/swarm:write
Read ${CLAUDE_PLUGIN_ROOT}/commands/launch.md and execute it in full — every step, in order — with these overrides:
- Mode: Writing, 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 command and point them to
/swarm:launch(or the matching shortcut) — do not switch modes mid-command. - Outcomes question (Step 2): "What are you writing?"
- User-Provided Context: the section 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.
User-Provided Context
$ARGUMENTS
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.
- 2d ago First seen · 20 lines · 6 tokens per session scan A 3f92625a20b4
write is a command published in the GitHub repository DheerG/swarms (86 stars, last pushed 1mo ago), licensed MIT. It adds 6 tokens to every session and 233 once invoked, about $0.0000 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.
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.