Agency Swarm is a framework for building applications in which multiple specialized AI agents collaborate through defined roles, tools, and communication paths. Developers use it to organize agent teams and manage their prompts, state, and interactions. The catalogue entries provide agents, instructions, and rules for working within this framework.
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.
git clone --depth 1 https://github.com/VRSEN/agency-swarmWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/vrsen/agency-swarm/writing-docs)<a href="https://agentmods.dev/rules/vrsen/agency-swarm/writing-docs"><img src="https://agentmods.dev/badge/rules/vrsen/agency-swarm/writing-docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/vrsen/agency-swarm/writing-docs"><img src="https://agentmods.dev/badge/rules/vrsen/agency-swarm/writing-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01280 | $0.01280 |
| Opus 5.5 | $0.00512 | $0.00512 |
| Sonnet 5.5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
writing-docs 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When writing or improving documentation for Agency Swarm, your primary goal is clarity for the target reader: show the information they need to complete the task, with enough context to avoid confusion.
Agency Swarm Documentation Writing Rules
- Write documentation in an easy to understand conversational language.
- Use simple language and clear terms.
- Docs should be easily readable by an 8th grader.
- Be concise, but keep full sentences and transitions when they are needed for readability.
- Make documentation actionable. Place code snippets at the top so users can easily copy and paste them. Provide only essential context above the code. Move any complex or detailed explanations to the end of the page.
- The more important the information is, the higher it should be on the page.
- Highlight the important parts by using bold, components, etc.
- Hide complexity under tabs, dropdowns, etc.
- Split pages into sub pages if needed. Use ~150 visible lines as a readability target, not a hard limit. Collapsed content (for example accordions) does not count toward this target.
Release Notes
Use these rules for release notes so the intro stays readable and every claim stays tied to a shipped change.
- Write the opening paragraph and each section intro for non-technical readers first. In one or two sentences, say what changed and why it matters in plain English.
- Ground every phrase in a concrete change from the repo or release diff. If a phrase cannot be tied to a command, API, capability, limit, or fix, delete it.
- Prefer plain verbs and nouns like
start,open,run,set up,use, andfix. - Avoid vague opener words like
documented,surface,workflow,path, andbehaviorunless the exact term is required for accuracy. - Keep the intro broad and easy to read, then let the bullets carry the exact commands, APIs, models, limits, PR numbers, and contributor names.
- Group sections by reader value, not by implementation layer.
- Do not present internal policy or agent-rule changes as public docs. If they must be included, label them as internal maintenance and keep them brief.
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.
- 22d ago Changed · +7 lines · +63 tokens per session 0bbbe65e1829
- 1mo ago First seen · 154 lines · 1,217 tokens per session scan A 3f47f3e8e915
writing-docs is a cursor rule published in the GitHub repository VRSEN/agency-swarm (4,614 stars, last pushed 3d ago), licensed MIT. It adds 1,280 tokens to every session, about $0.0051 per session on Opus 5.5. 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .