Borrowing it
Nothing to install: this file belongs to mangeshraut712/Gravity-SaaS-Agent. 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/mangeshraut712/Gravity-SaaS-Agent/main/AGENTS.mdgit clone --depth 1 https://github.com/mangeshraut712/Gravity-SaaS-AgentWrote 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/mangeshraut712/gravity-saas-agent/agents-md)<a href="https://agentmods.dev/instructions/mangeshraut712/gravity-saas-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/mangeshraut712/gravity-saas-agent/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/mangeshraut712/gravity-saas-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/mangeshraut712/gravity-saas-agent/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 | $0.00414 | $0.00414 |
| Opus 5.5 | $0.00166 | $0.00166 |
| Sonnet 5.5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
Gravity-SaaS-Agent 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 1mo 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.
What it actually says
AGENTS.md — Gravity SaaS Agent
Guidance for coding agents working in this monorepo.
Layout (npm workspaces)
apps/gateway— Express API gateway: channel adapters (web, WhatsApp, Telegram, API), rate limiter, circuit breaker, skills engine, MCP client, caching.apps/dashboard— Next.js 15.5 operator dashboard.packages/db,packages/mcp-client,packages/memory,packages/types— shared libraries.supabase/— schema and Row Level Security policies.
Setup and verification
npm install
npm run dev # gateway + dashboard concurrently
npm run validate # typecheck + lint + test (also runs on pre-push)
npm run test:ci # coverage
npm run docker:up # full stack via docker-compose
Hard rules
- Tenant isolation is enforced in the database. Every new table needs an RLS policy in
supabase/; never rely on application-level filtering alone. - Keep the guardrails on the model path: tier-based rate limits (Free 10 / Pro 100 / Business 1000 req/min), the circuit breaker, and the OpenRouter multi-model fallback. A feature that bypasses them is a bug.
- Treat
billing_eventsand analytics events as append-only (they are event logs); add new rows rather than mutating history, and add a policy insupabase/schema.sqlif you need to enforce it. - Secrets come from environment variables only. No keys in code, fixtures, or docs.
- Run
npm run validatebefore proposing a change; workspaces must typecheck independently.
Where to look first
README.md→ Architecture section for the request path (channel adapter → gateway → skills/MCP → model).SECURITY.mdfor disclosure and hardening notes.
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.
- 1mo ago First seen · 39 lines · 414 tokens per session scan A 95e418d7e30b
Gravity-SaaS-Agent AGENTS.md is an instructions file published in the GitHub repository mangeshraut712/Gravity-SaaS-Agent (8 stars, last pushed 3d ago), licensed MIT. It adds 414 tokens to every session, about $0.0017 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 2026-09-17.
Gravity-SaaS-Agent AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Gravity-SaaS-Agent AGENTS.mdmangeshraut712/Gravity-SaaS-Agent | Instructions file | 8 | 3d ago | MIT | A | 414 | Codex, OpenCode |
| plan-forge deploy.instructions.mdsrnichols/plan-forge | Instructions file | 6 | 2d ago | MIT | A | 1,667 | GitHub Copilot |
| plan-forge azd.instructions.mdsrnichols/plan-forge | Instructions file | 6 | 2d ago | MIT | A | 1,500 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |