swarm-web-research

swarm-web-research is a command for Claude Code, OpenCode from d-o-hub/github-template-ai-agents. It costs 16 tokens per session (150 once invoked), scanned A, original, MIT.

A command that coordinates several agents to research a topic, combine their findings, and create a GitHub pull request with the resulting report.

In plain words
What is it for?
Use it for multi-agent web research and consolidated codebase or topic analysis saved to a Markdown file.
Why use it?
It organizes broad investigations in an isolated worktree and reduces the effort of collecting, comparing, and publishing research results.

Command for Claude CodeOpenCode

Written for Claude Code and OpenCode: $ARGUMENTS substitution, but also installed under .opencode/.

Good fit Use it for multi-agent web research and consolidated codebase or topic analysis saved to a Markdown file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/d-o-hub/github-template-ai-agents/swarm-web-research
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.

Clone the repo
git clone --depth 1 https://github.com/d-o-hub/github-template-ai-agents

Made for: Claude Code, OpenCode.

Wrote 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.

agentmods badge for swarm-web-research

README.md
[![agentmods](https://agentmods.dev/badge/commands/d-o-hub/github-template-ai-agents/swarm-web-research.svg)](https://agentmods.dev/commands/d-o-hub/github-template-ai-agents/swarm-web-research)
Your own site
<a href="https://agentmods.dev/commands/d-o-hub/github-template-ai-agents/swarm-web-research"><img src="https://agentmods.dev/badge/commands/d-o-hub/github-template-ai-agents/swarm-web-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 150 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.00150
Opus 5 $0.00008 $0.00075
Sonnet 5 $0.00003 $0.00030
Haiku 4.5 $0.00002 $0.00015

Measured 4d ago against content hash 1de1bb2a860c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

swarm-web-research 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 4d 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.

.opencode/commands/swarm-web-research.md · 20 lines

What it actually says

Execute multi-agent swarm analysis using git worktrees with optimized web research.

Topic: $ARGUMENTS

Steps:

  1. Load skills: do-web-doc-resolver, agent-coordination, git-github-workflow
  2. Create git worktree for isolated analysis
  3. Execute web research using the resolver skill with optimized cascade
  4. Launch 3-agent swarm in parallel using task tool
  5. Synthesize findings into consolidated report
  6. Create PR with all analysis files
  7. Monitor GitHub Actions until checks pass

Save findings to analysis/SWARM_SYNTHESIS.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. 4d ago First seen · 20 lines · 16 tokens per session scan A 1de1bb2a860c

Subscribe to this mod's changes

swarm-web-research is a command published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 150 once invoked, about $0.0001 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 2026-09-03.