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/christopherkarani/swarm/agents-mdgit clone --depth 1 https://github.com/christopherkarani/SwarmWhat 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 | $0.00377 | $0.00377 |
| Opus 5 | $0.00188 | $0.00188 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
Swarm AGENTS.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
Agent Instructions
Public Repository Hygiene
This is the front-facing Swarm GitHub repository. Keep tracked files limited to source code, tests, examples, public documentation, release tooling, and CI.
Do not add or re-track internal planning, audit, marketing, or assistant workspace artifacts. In particular, keep these paths out of Git:
tasks/.claude/.agent_context.md.mcp.jsondocs/plans/docs/prompts/docs/superpowers/docs/work-packages/docs/validation/marketing/website/IMPLEMENTATION_PLAN.mdHIVE_EXTENSIBILITY_INTEGRATION_PLAN.mdPRODUCTION_READINESS_AUDIT.mddocs/reference/*audit-report.mddocs/reference/documentation-*-report.mddocs/reference/documentation-improvement-plan.mddocs/reference/api-quality-assessment.mddocs/reference/twitter-article-*.mddocs/swarm-hacker-news-blog.md
If a task requires one of those artifacts, keep it local only. Before staging,
run git status --short and make sure none of the paths above are staged. If a
future cleanup finds one tracked again, remove it from Git instead of editing it
as public documentation.
Development Rules
- Preserve unrelated dirty worktree changes.
- Keep edits surgical and matched to the requested behavior.
- Use tests for behavioral changes.
- For public API changes, update source DocC and the remaining public reference
docs:
README.md,docs/guide/*,docs/reference/overview.md,docs/reference/front-facing-api.md, anddocs/reference/api-catalog.md.
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 · 45 lines · 377 tokens per session scan A 9445a977bb94
Swarm AGENTS.md is an instructions file published in the GitHub repository christopherkarani/Swarm (574 stars, last pushed 3d ago), licensed MIT. It adds 377 tokens to every session, about $0.0019 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 instructions, from other repositories
LangAlpha AGENTS.md
AGENTS.md instructions for ginlix-ai/LangAlpha, covering langalpha, common commands, architecture, backend (src/) and frontend (web/src/).
flock AGENTS.md
Instructions for Onelevenvy/flock, covering agents.md, project overview, build & development commands, rust backend and build the cli.
swift-architecture-skill AGENTS.md
Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.
LangAlpha CLAUDE.md
Claude Code instructions for ginlix-ai/LangAlpha: Agent context for this repo lives in AGENTS.md — the vendor-neutral single source of truth, read directly by Codex/Cursor/Copilot/etc. Claude Code reads THIS file and expands the @import below, so every toolchain gets identical context. Edit AGENTS.md, not this file.…
Dingent AGENTS.md
Instructions for Dingent/Dingent, covering dingent agentic coding instructions (agents.md), 1. project context & architecture, 2. environment & commands, prerequisites and build & run.
dive-into-langgraph AGENTS.md
AGENTS.md instructions for luochang212/dive-into-langgraph, covering agents.md, how we work, what this project is, project layout and environment & toolchain.