What is metaswarm GEMINI.md?

Instructions for Metaswarm, a software-development system that coordinates specialized agents and requires checks such as TDD, or writing tests before implementation.

Starting tracked tasks, loading project knowledge, reviewing designs, shepherding pull requests through merging, handling review comments, creating issues, configuring the system, and running diagnostics.

It gives developers a defined workflow for starting work, reviewing designs, checking progress, and handling pull requests instead of managing each step manually.

How dsifry/metaswarm configures Gemini CLI

Reuse

Borrowing it

Nothing to install: this file belongs to dsifry/metaswarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dsifry/metaswarm/main/GEMINI.md

Clone the repo

git clone --depth 1 https://github.com/dsifry/metaswarm

Made for: Gemini CLI.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dsifry/metaswarm/gemini-md/github.svg)](https://agentmods.dev/instructions/dsifry/metaswarm/gemini-md)

Your own site

<a href="https://agentmods.dev/instructions/dsifry/metaswarm/gemini-md"><img src="https://agentmods.dev/badge/instructions/dsifry/metaswarm/gemini-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dsifry/metaswarm/gemini-md"><img src="https://agentmods.dev/badge/instructions/dsifry/metaswarm/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,222 This file is loaded in full into every session.

When invoked 1,222 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01222	$0.01222
Opus 5.5	$0.00489	$0.00489
Sonnet 5.5	$0.00244	$0.00244
Haiku 4.5	$0.00122	$0.00122

Measured today against content hash 95c5465e0dd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

metaswarm GEMINI.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 today.

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.

GEMINI.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

metaswarm

Multi-agent orchestration framework for software development. 22 agents (+3 deprecated), 14 skills, quality gates, TDD enforcement.

Getting Started

Run /metaswarm:start-task to begin tracked work, or /metaswarm:setup to configure metaswarm for this project.

Available Commands

Command	Purpose
`/metaswarm:start-task`	Begin tracked work on a task
`/metaswarm:prime`	Load relevant knowledge before starting
`/metaswarm:review-design`	Trigger design review gate (5 reviewers)
`/metaswarm:pr-shepherd`	Monitor a PR through to merge
`/metaswarm:self-reflect`	Extract learnings after a PR merge
`/metaswarm:handle-pr-comments`	Handle PR review comments
`/metaswarm:brainstorm`	Refine an idea before implementation
`/metaswarm:create-issue`	Create a well-structured GitHub Issue
`/metaswarm:external-tools-health`	Check status of external AI tools
`/metaswarm:setup`	Interactive guided setup
`/metaswarm:status`	Run diagnostic checks

Workflow

For complex features, describe what you want with a Definition of Done and say: Use the full metaswarm orchestration workflow.

This runs: Research -> Plan -> Design Review Gate -> Work Unit Decomposition -> Orchestrated Execution (4-phase loop per unit) -> Final Review -> PR.

Quality Gates (MANDATORY)

After brainstorming -> MUST run /metaswarm:review-design before planning
After any plan -> MUST run Plan Review Gate before presenting to user
Before finishing branch -> MUST run /metaswarm:self-reflect before PR
Coverage -> .coverage-thresholds.json is the single source of truth. BLOCKING gate.
TDD is mandatory -> Write tests first, watch them fail, then implement

Rules

NEVER use --no-verify on git commits
NEVER use git push --force without explicit user approval
ALWAYS follow TDD
STAY within declared file scope

Delivery Scope & Review Iteration

Block delivery only for a credible normal-usage failure, a missing or contradictory requirement, a broken key happy path, or an important error or recovery-path failure. Every review finding carries a severity (critical/major/minor/nit); to block, a critical/major finding must also name what it protects (a user scenario, requirement or DoD item). Findings without protects are advisory, not blockers. After each review round the orchestrator decides whether to iterate, advance or escalate:

Read the full file on GitHub · 80 lines

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.

today Changed · +25 lines · +674 tokens per session 95c5465e0dd3
2mo ago First seen · 55 lines · 548 tokens per session scan A 29367cfa05ef

Subscribe to this mod's changes

metaswarm GEMINI.md is an instructions file published in the GitHub repository dsifry/metaswarm (425 stars, last pushed today), licensed MIT. It adds 1,222 tokens to every session, about $0.0049 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.

metaswarm GEMINI.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
metaswarm GEMINI.mddsifry/metaswarm	Instructions file	425	today	MIT	A	1,222	Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

metaswarm: Instructions file for Gemini CLI