Swarm AGENTS.md

Repository instructions for Swarm, a Swift framework for building agents and multi-step workflows. They also define which internal files must stay out of the public repository and give development rules.

In plain words
What is it for?
Use them when changing Swarm source, tests, documentation, release files, or Git-tracked content.
Why use it?
They help coding agents follow the project’s public-repository boundaries and development practices.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/christopherkarani/swarm/agents-md
Clone the repo
git clone --depth 1 https://github.com/christopherkarani/Swarm

Made for: Codex, OpenCode.

Per session 377 This file is loaded in full into every session.
When invoked 377 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 9445a977bb94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 45 lines

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.json
  • docs/plans/
  • docs/prompts/
  • docs/superpowers/
  • docs/work-packages/
  • docs/validation/
  • marketing/
  • website/
  • IMPLEMENTATION_PLAN.md
  • HIVE_EXTENSIBILITY_INTEGRATION_PLAN.md
  • PRODUCTION_READINESS_AUDIT.md
  • docs/reference/*audit-report.md
  • docs/reference/documentation-*-report.md
  • docs/reference/documentation-improvement-plan.md
  • docs/reference/api-quality-assessment.md
  • docs/reference/twitter-article-*.md
  • docs/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, and docs/reference/api-catalog.md.
Changes

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.

  1. 2d ago First seen · 45 lines · 377 tokens per session scan A 9445a977bb94

Subscribe to this mod's changes

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.

Related

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/).

ginlix-ai/LangAlpha · 2,596 tokens

flock AGENTS.md

Instructions for Onelevenvy/flock, covering agents.md, project overview, build & development commands, rust backend and build the cli.

Onelevenvy/flock · 2,131 tokens

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.

efremidze/swift-architecture-skill · 987 tokens

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.…

ginlix-ai/LangAlpha · 83 tokens

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.

Dingent/Dingent · 2,088 tokens

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.

luochang212/dive-into-langgraph · 670 tokens