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 instructions/spranab/swarmcode/claude-mdgit clone --depth 1 https://github.com/spranab/swarmcodeWhat 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 | $0.00254 | $0.00254 |
| Opus 5 | $0.00127 | $0.00127 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
swarmcode CLAUDE.md 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
SwarmCode
Real-time communication between Claude Code instances across machines and workspaces.
Architecture
src/channel.js- MCP server with swarm_send/receive/status/register tools + Redis pub/subsrc/listener.js- One-shot Redis listener for background task notificationssrc/check-inbox-http.js- Hook script for inbox check on each promptsrc/init.js- CLI to initialize any workspace in one commandsrc/server.js- CLI entry point (routes to init/channel/listen)
Key Design
- Redis pub/sub for real-time cross-machine messaging
- Per-workspace channels:
swarmcode:ws:<workspace-id> - Broadcast channel:
swarmcode:ws:broadcast - Background task pattern: listener exits on message → task-notification → auto-process
- Messages stored in per-workspace inbox lists with 24h TTL
Running
npx swarmcode init <workspace-id> --redis redis://host:port
Environment
SWARMCODE_REDIS_URL- Redis URL (default: redis://localhost:6379)SWARMCODE_WORKSPACE_ID- Workspace identifier
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 · 27 lines · 254 tokens per session scan A 74f53a772920
swarmcode CLAUDE.md is an instructions file published in the GitHub repository spranab/swarmcode (8 stars, last pushed 14d ago), licensed MIT. It adds 254 tokens to every session, about $0.0013 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 instructions, from other repositories
conductor AGENTS.md
Instructions for conductor-oss/conductor, covering agents.md, project overview, setup commands, java version references and code style.
go-micro CLAUDE.md
Instructions for micro/go-micro, covering claude.md - go micro project guide, project overview, build & test, run all tests and run tests for a specific package.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
sema AGENTS.md
Instructions for emergent-wisdom/sema, covering repository agent guide, development workflow, vocabulary changes, vocabulary review and the improvement loop, per pattern.
Bindu CLAUDE.md
Claude Code instructions for GetBindu/Bindu, covering project: bindu - decentralized agent framework, critical context (read first), what is bindu?, commands that work and python core development.
chronos CLAUDE.md
Instructions for sx4im/chronos, covering claude.md — chronos, what this project is, the prime directive (never violate), the core mental model (why dst works here) and the non-negotiable contract for users.