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.
npx agentmods add instructions/stormlive-ai/ag-sdd/agents-mdgit clone --depth 1 https://github.com/stormlive-ai/ag-sddWrote 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/instructions/stormlive-ai/ag-sdd/agents-md)<a href="https://agentmods.dev/instructions/stormlive-ai/ag-sdd/agents-md"><img src="https://agentmods.dev/badge/instructions/stormlive-ai/ag-sdd/agents-md.svg" alt="Measured on agentmods" 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 | $0.02613 | $0.02613 |
| Opus 5 | $0.01307 | $0.01307 |
| Sonnet 5 | $0.00523 | $0.00523 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade A, and why
ag-sdd 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 5d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Anti-Gravity Spec-Driven Development (ag-sdd)
This file is the primary steering entry point for any Anti-Gravity agent operating within a repository that uses the
ag-sddworkflow. Every instruction below is non-negotiable. Violations constitute a failed task.
1. Purpose & Philosophy
ag-sdd enforces a Spec-Driven Development methodology where every non-trivial code change is governed by a structured specification pipeline. The core guarantee:
No code is written until a specification exists, has been decomposed into atomic tasks, and the agent has passed a clarification gate.
This eliminates the two most common failure modes of agentic coding:
- Thin Thinking — collapsing complex work into a handful of vague tasks.
- Boundary Violations — modifying files outside the declared scope of a task.
2. SDD Workflow Lifecycle
Every non-trivial prompt passes through exactly four phases. No phase may be skipped.
┌─────────────────────────────────────────────────────────────────────┐
│ SDD WORKFLOW LIFECYCLE │
│ │
│ ┌──────────┐ ┌──────────┐ ┌──────────────┐ ┌──────────┐ │
│ │ DISCOVERY│───▶│ SPEC GEN │───▶│ SEQUENTIAL │───▶│ QUALITY │ │
│ │ │ │ │ │ EXECUTION │ │ SIGNOFF │ │
│ └──────────┘ └──────────┘ └──────────────┘ └──────────┘ │
│ │
│ Phase 1: Phase 2: Phase 3: Phase 4: │
│ Clarification Generate spec Execute tasks Run full │
│ Gate (3-5 Qs) artifacts in ONE per context verification │
│ .specs/ pass, verify, suite, update │
│ propagate notes signoff log │
└─────────────────────────────────────────────────────────────────────┘
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.
- 5d ago First seen · 253 lines · 2,613 tokens per session scan A 72956d82cb33
ag-sdd AGENTS.md is an instructions file published in the GitHub repository stormlive-ai/ag-sdd (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,613 tokens to every session, about $0.0131 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 2026-08-31.
Other instructions, from other repositories
AntigravityManager AGENTS.md
AGENTS.md instructions for Draculabo/AntigravityManager, covering antigravity manager agent instructions, communication, environment and tools, standing architecture rules and type and api design.
AntigravityManager CLAUDE.md
Claude Code instructions for Draculabo/AntigravityManager, a project described as: Antigravity Manager is a powerful Electron-based application designed to manage accounts and processes for the Antigravity application. It provides a seamless interface for switching accounts, backing up progress, and controlling the…
SaaS-blueprint AGENTS.md
AGENTS.md instructions for tuliosousapro/SaaS-blueprint, covering agents.md, repository overview, repository structure, build / lint / test commands and agent skills specification.
agy-plugin-cc CLAUDE.md
Instructions for Vit129/agy-plugin-cc, covering agy-plugin-cc — claude code guide, agent memory, global-first rule, project context (auto-loaded every session) and project summary.
antigravity-awesome-group-skills AGENTS.md
AGENTS.md instructions for may215/antigravity-awesome-group-skills, covering agents.md — instructions for ai coding assistants, what is this repository?, repository structure, how skills work and when to reference a skill.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).