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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/gracenoble/fullstack-template/claude-md"><img src="https://agentmods.dev/badge/instructions/gracenoble/fullstack-template/claude-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 | $0.02671 | $0.02671 |
| Opus 5 | $0.01336 | $0.01336 |
| Sonnet 5 | $0.00534 | $0.00534 |
| Haiku 4.5 | $0.00267 | $0.00267 |
Grade A, and why
fullstack-template CLAUDE.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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Guide
Stack
| Layer | Tech |
|---|---|
| Frontend | Next.js 16, React 19, TypeScript 5, Tailwind CSS 4 |
| Backend | Go 1.25, Gin, database/sql + pgx v5 stdlib |
| Database | PostgreSQL 16 via Docker Compose |
| Mobile | Android, Kotlin 2.2, Jetpack Compose BOM 2026.02, Material3 |
| Dev tools | pnpm, Air (Go hot reload), Testcontainers, Gradle 9.4 |
Run commands
cd backend && make docker-run # start Postgres
cd backend && make watch # backend dev with hot reload (Air) → :8080
cd web && pnpm dev # web dev → :3000
cd backend && make test # all tests
cd backend && make itest # integration tests only (requires Docker)
cd web && pnpm lint && pnpm build
cd web && pnpm test # Vitest unit + component tests
cd web && pnpm test:watch # watch mode during TDD
cd mobile && ./gradlew assembleDebug # build Android APK
cd mobile && ./gradlew lint && ./gradlew test # mobile quality gate
cd mobile && ./gradlew connectedAndroidTest # instrumented tests (emulator/device required)
Migration commands (run from backend/)
make migrate-create name=<slug> # create a new timestamped SQL migration file
make migrate-status # show applied vs. pending migrations
make migrate-up # apply all pending migrations
make migrate-up-one # apply the next pending migration only
make migrate-down # roll back the last applied migration
make migrate-reset # roll back everything to version 0
make migrate-version # print current schema version
Feature development workflow — always follow this
- Check docs first — delegate to
docsagent: find relevant topic docs, verify they match the current code - Fix stale docs — if docs diverge from code, update docs before implementing
- Migrate — if the feature needs new or changed tables:
make migrate-create name=<slug>, write the SQL,make migrate-up - Write tests first (TDD) — write failing tests that describe the intended behaviour before writing any implementation code
- Implement — delegate to
backendorwebagent, passing the relevant doc content as context; implementation is complete when all tests pass - Env vars — if any new env vars were added to
loadConfig(), add them tobackend/.env.examplewith a safe placeholder value and a comment explaining the format - Update docs — delegate to
docsagent: updatelast_verified, add new topics if introduced - Quality gate — run
/project:checkbefore declaring done
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 · 204 lines · 2,671 tokens per session scan A 722205104be4
fullstack-template CLAUDE.md is an instructions file published in the GitHub repository GRACENOBLE/fullstack-template (6 stars, last pushed 4d ago), licensed MIT. It adds 2,671 tokens to every session, about $0.0134 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
compiler-explorer AGENTS.md
AGENTS.md instructions for compiler-explorer/compiler-explorer, covering agents.md, build & test commands, important workflow requirements, style guidelines and architecture guidelines.
chatgpt-cli AGENTS.md
AGENTS.md instructions for kardolus/chatgpt-cli, covering agents.md, 1) repo map (where things usually live), 2) build & test workflow (use makefile first), 3) go version and 4) testing expectations (required).
hitkeep AGENTS.md
AGENTS.md instructions for PascaleBeier/hitkeep, covering hitkeep agent guide, start here, product invariants, repository map and contributor workflow.
pcmi AGENTS.md
AGENTS.md instructions for marco-spagn/pcmi, covering pcmi guidelines for ai coding agents, mandatory first reads, critical invariants (do not violate), preferred workflow for non-trivial tasks and area-specific notes.
klaudiush AGENTS.md
AGENTS.md instructions for smykla-skalski/klaudiush, a project described as: A validation dispatcher for Claude Code hooks that enforces git workflow standards, commit message conventions, and code quality rules.
spellbook AGENTS.md
AGENTS.md instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.