gsd-core GEMINI.md

Project instructions for GSD Core, a workflow system that turns a software goal into planned, tested, and shippable work. It organizes work into milestones and phases, with saved specifications and plans.

In plain words
What is it for?
Exploring a goal, writing a plan, executing small test-backed changes, verifying the result, and preparing the work for release through Antigravity CLI.
Why use it?
They keep development work organized and resumable by recording decisions and verification criteria in project files instead of relying only on chat history.

Instructions file for Gemini CLI

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/open-gsd/gsd-core/gemini-md
Clone the repo
git clone --depth 1 https://github.com/open-gsd/gsd-core

Made for: Gemini CLI.

Per session 611 This file is loaded in full into every session.
When invoked 611 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 $0.00611 $0.00611
Opus 5 $0.00305 $0.00305
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured yesterday against content hash 264c71c5c9d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd-core 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 yesterday.

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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GSD Core — Antigravity CLI context

Gemini CLI was sunset by Google on 2026-06-18 and is no longer served for free/Pro/Ultra tiers. Antigravity CLI is its official successor, and this file is the context Antigravity reads automatically (its contextFileName is GEMINI.md, inherited from the shared Gemini 3 backend).

This context gives Antigravity the operating context for GSD Core, a meta-prompting, context-engineering, and spec-driven development system for AI coding agents.

What GSD is

GSD turns a vague goal into shipped software through an explicit, resumable workflow: explore → plan → execute → verify → ship. Work is organised into milestones and phases under a .planning/ directory, with each phase carrying a SPEC, a PLAN, and verification criteria. The system favours small, atomic, test-backed commits and keeps durable context in version-tracked files rather than in the conversation.

The slash commands (installed separately)

This file ships only the context above — not the slash commands. To install the /gsd-* command set, agents, and hooks into ~/.gemini/antigravity/, run the dedicated installer:

npx gsd-core --antigravity --global

The commands below are available only once that installer has run.

If you have installed the gsd commands, the workflow is driven by these /gsd-* slash commands (Antigravity registers gsd's commands under a hyphenated namespace):

  • /gsd-new-project — initialise a project and gather deep context.
  • /gsd-progress — the unified situational command: check progress, advance the workflow, or dispatch a freeform intent.
  • /gsd-plan-phase <N> — produce a detailed phase plan with a verification loop.
  • /gsd-execute-phase <N> — execute a phase's plans with wave-based parallelism.
  • /gsd-verify-work — validate built features through conversational UAT.
  • /gsd-ship — open a PR, run review, and prepare for merge.
  • /gsd-help — list every available command.

Read the full file on GitHub · 56 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.

  1. yesterday First seen · 56 lines · 611 tokens per session scan A 264c71c5c9d5

Subscribe to this mod's changes

gsd-core GEMINI.md is an instructions file published in the GitHub repository open-gsd/gsd-core (8,909 stars, last pushed 2d ago), licensed MIT. It adds 611 tokens to every session, about $0.0031 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

get-shit-done AGENTS.md

Instructions for gsd-build/get-shit-done, covering repository guidelines, active discussions, project structure & module organization, build, test, and development commands and coding style & naming conventions.

gsd-build/get-shit-done · 739 tokens

get-shit-done-multi copilot-instructions.md

Copilot instructions for shoootyou/get-shit-done-multi, a project described as: Fork of Get Shit Done (TÂCHES) with multi-CLI support. Spec-driven development workflows for Claude, Copilot, and Codex with unified project state.

shoootyou/get-shit-done-multi · 103 tokens

get-shit-done-multi CLAUDE.md

Claude Code instructions for shoootyou/get-shit-done-multi, a project described as: Fork of Get Shit Done (TÂCHES) with multi-CLI support. Spec-driven development workflows for Claude, Copilot, and Codex with unified project state.

shoootyou/get-shit-done-multi · 105 tokens

get-shit-done-multi AGENTS.md

AGENTS.md instructions for shoootyou/get-shit-done-multi, a project described as: Fork of Get Shit Done (TÂCHES) with multi-CLI support. Spec-driven development workflows for Claude, Copilot, and Codex with unified project state.

shoootyou/get-shit-done-multi · 105 tokens

terminal-jarvis AGENTS.md

Instructions for BA-CalderonMorales/terminal-jarvis, covering agents.md - terminal jarvis, current shape, key sections, branch strategy and merge-to-develop discipline.

BA-CalderonMorales/terminal-jarvis · 2,206 tokens

dev-workflow CLAUDE.md

Instructions for andreaserradev-gbj/dev-workflow, covering claude.md, project overview, repository structure, generated in user's project (not in plugin repo) and development.

andreaserradev-gbj/dev-workflow · 2,782 tokens