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/khaledsaeed18/node-express-boilerplate/agents-mdgit clone --depth 1 https://github.com/KhaledSaeed18/node-express-boilerplateWrote 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/khaledsaeed18/node-express-boilerplate/agents-md)<a href="https://agentmods.dev/instructions/khaledsaeed18/node-express-boilerplate/agents-md"><img src="https://agentmods.dev/badge/instructions/khaledsaeed18/node-express-boilerplate/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 | $0.01179 | $0.01179 |
| Opus 5 | $0.00589 | $0.00589 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
node-express-boilerplate 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 3d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Canonical instructions for AI coding agents working in this repository. CLAUDE.md, GEMINI.md, and .github/copilot-instructions.md are symlinks to this file — edit only this file.
Read First
- Project overview and architecture: README.md
- Setup and contributor workflow: CONTRIBUTING.md
Skills
Reusable workflows live in .agents/skills/ (source of truth; .claude/skills/ contains symlinks into it). Prefer a skill when the request matches one:
Project workflows:
new-resource— scaffold a complete API resource end to endupdate-schema— Prisma schema change + migration + client regen + downstream updatesadd-middleware— create and wire Express middlewareadd-test— scaffold unit and integration tests for a resourceadd-openapi-docs— document endpoints insrc/docs/(schemas, paths, registration)security-audit— project-specific security review (auth, CSRF, limits, validation, secrets)
Reference guidance:
prisma-client-api,prisma-database-setup,prisma-postgres— Prismavitest— Vitest testing patternsapi-design-principles— REST API designnodejs-best-practices— Node.js patterns and decision-makingmulti-stage-dockerfile— optimized Dockerfilestypescript-magician— advanced TypeScript typingfind-skills— discover and install new skills
When no skill matches, follow this file directly.
Working Style
- Keep edits small and localized; avoid broad refactors unless explicitly requested.
- Preserve current architecture and naming conventions.
- After code changes, run
pnpm full-checkand the most relevant test suite before finishing.
Stack
Node.js 22+ · Express 5 · TypeScript 6 (strict) · Prisma 7 + PostgreSQL 16 · Zod v4 · Pino · JWT (HttpOnly cookies) · CSRF (double-submit cookie) · Vitest · pnpm
Required Commands
# Development
pnpm dev
pnpm build
pnpm start
# Quality gate (run before finalizing changes)
pnpm full-check
# Focused checks
pnpm lint
pnpm format
pnpm type-check
pnpm knip # dead code / unused deps (enforced in CI)
# Prisma
pnpm prisma:migrate
pnpm prisma:migrate:deploy
pnpm prisma:generate
pnpm prisma:db:seed
# Tests
pnpm test
pnpm test:integration
pnpm test:all
pnpm db:test:up
pnpm db:test:migrate
pnpm db:test:down
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.
- 3d ago First seen · 128 lines · 1,179 tokens per session scan A 857f153c5a36
node-express-boilerplate AGENTS.md is an instructions file published in the GitHub repository KhaledSaeed18/node-express-boilerplate (33 stars, last pushed 10d ago), licensed MIT. It adds 1,179 tokens to every session, about $0.0059 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 2026-08-30.
Other instructions, from other repositories
kerberos AGENTS.md
Instructions for mongodb-js/kerberos, covering agents.md, project overview, commands, structure and code conventions.
kerberos CLAUDE.md
Instructions for mongodb-js/kerberos, a project described as: Kerberos library for node.js.
pi-anthropic-auth AGENTS.md
Instructions for gotgenes/pi-anthropic-auth, covering agents guide: pi-anthropic-auth, project, primary goal, current status and principles.
zapo CLAUDE.md
Instructions for vinikjkkj/zapo: The contributor handbook for this repository lives in AGENTS.md. Read that file and follow it as your primary source of project conventions, architecture rules, performance constraints, and review anti-patterns.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).
SoDam-WikiMate AGENTS.md
Instructions for sodam-ai/SoDam-WikiMate, covering wikimate 작업 규칙 (크로스툴 — claude code · codex · gemini 공용), 문체, 자동 동작 (자연어 트리거 — 강제 호출 불필요), 접근 규칙 (자동 감지 — 특정 도구에 한정하지 않음) and obsidian 규칙.