Borrowing it
Nothing to install: this file belongs to stormlive-ai/ag-sdd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stormlive-ai/ag-sdd/master/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/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/instructions/stormlive-ai/ag-sdd/agents-md"><img src="https://agentmods.dev/badge/instructions/stormlive-ai/ag-sdd/agents-md.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 | $0.02613 | $0.02613 |
| Opus 5.5 | $0.01045 | $0.01045 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (4 stars, last pushed 3mo ago), licensed MIT. It adds 2,613 tokens to every session, about $0.0105 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 2026-08-31.
ag-sdd AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ag-sdd AGENTS.mdstormlive-ai/ag-sdd | Instructions file | 4 | 3mo ago | MIT | A | 2,613 | Codex, OpenCode |
| 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 |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |