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/gracenoble/fullstack-template/agents-mdgit clone --depth 1 https://github.com/GRACENOBLE/fullstack-templateWrote 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/gracenoble/fullstack-template/agents-md)<a href="https://agentmods.dev/instructions/gracenoble/fullstack-template/agents-md"><img src="https://agentmods.dev/badge/instructions/gracenoble/fullstack-template/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 | $0.00987 | $0.00987 |
| Opus 5 | $0.00494 | $0.00494 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
fullstack-template 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 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Fullstack project — Go + Gin backend, Next.js 16 + React 19 web app, PostgreSQL, Android mobile (Kotlin + Compose).
Each layer has its own AGENTS.md and docs/ folder. Read the file closest to what you are editing:
backend/AGENTS.md+backend/docs/— Go APIweb/AGENTS.md+web/docs/— Next.js UImobile/AGENTS.md+mobile/docs/— Android app
Claude Code users: see CLAUDE.md for the feature development workflow and subagent definitions.
Setup
Prerequisites: Go 1.21+, Node.js 20+, pnpm, Docker + Docker Compose, Android Studio Meerkat (2024.3+), JDK 17+, Android SDK API 36.
# 1. Database
cd backend && make docker-run
# 2. Backend API (hot reload, separate terminal)
cd backend && make watch # → http://localhost:8080
# 3. Web app (separate terminal)
cd web && pnpm install && pnpm dev # → http://localhost:3000
# 4. Mobile — open mobile/ in Android Studio and run on emulator/device
cd mobile && ./gradlew assembleDebug # build only
cd mobile && ./gradlew installDebug # build and install on connected device
Testing
TDD is required. Write failing tests first, then implement.
# Backend (Docker must be running)
cd backend && make test # unit + integration
cd backend && make itest # integration only
# Web
cd web && pnpm test # Vitest unit + component tests
cd web && pnpm test:watch # watch mode during development
cd web && pnpm lint
cd web && pnpm build
# Mobile
cd mobile && ./gradlew lint
cd mobile && ./gradlew test # unit tests (no device needed)
cd mobile && ./gradlew connectedAndroidTest # instrumented tests (emulator/device required)
- Backend DB and cache tests use Testcontainers (real PostgreSQL, real Redis). Never mock the database.
- Web unit/component tests use Vitest + @testing-library/react. Server Component flows use Playwright (future).
- Mobile Composable tests use Compose test rules in instrumented tests.
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 First seen · 106 lines · 987 tokens per session scan A 83dbadae8dbe
fullstack-template AGENTS.md is an instructions file published in the GitHub repository GRACENOBLE/fullstack-template (6 stars, last pushed 4d ago), licensed MIT. It adds 987 tokens to every session, about $0.0049 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 2026-09-04.
Other instructions, from other repositories
sq AGENTS.md
Instructions for neilotoole/sq, covering agents.md, about sq, key documents, common commands and conventions.
cli AGENTS.md
AGENTS.md instructions for planetscale/cli, covering planetscale cli — agent guide, public repository safety, concepts, flag placement and correct.
cockroach CLAUDE.md
Claude Code instructions for cockroachdb/cockroach, covering claude.md, cockroachdb development environment, essential commands, build package ./pkg/util/log and build the tests in package ./pkg/util/log.
GoSQLX CLAUDE.md
Instructions for ajitpratap0/GoSQLX, covering claude.md, project overview, architecture, core components and token processing pipeline.
vc-gin-api AGENTS.md
Instructions for bg-vc/vc-gin-api, covering vc-gin-api agent guide, product rule: simple and change workflow.
nlp2sql CLAUDE.md
Claude Code instructions for luiscarbonel1991/nlp2sql, covering claude.md, project overview, documentation, development commands and install dependencies.