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/hmake98/nestjs-starter/servicesgit clone --depth 1 https://github.com/hmake98/nestjs-starterWhat 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 | $0.00151 | $0.00151 |
| Opus 5 | $0.00076 | $0.00076 |
| Sonnet 5 | $0.00030 | $0.00030 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade A, and why
nestjs-starter services.instructions.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 2d 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
Service Conventions
- Inject repositories, not
DatabaseServicedirectly. - Logger:
private readonly logger = new Logger(ClassName.name). Only callthis.logger.error(...)for unexpected 5xx failures. - Repeated existence checks: extract
private async assertExists(id: string): Promise<void>usingexistsById. - All errors:
throw new HttpException('domain.error.key', HttpStatus.STATUS)— always an i18n key string, never a raw message. - Config access:
this.configService.getOrThrow<string>('domain.nested.key')— neverprocess.env. - Return typed response DTOs, not raw Prisma entities.
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.
- 2d ago First seen · 13 lines · 151 tokens per session scan A 29f1862adb20
nestjs-starter services.instructions.md is an instructions file published in the GitHub repository hmake98/nestjs-starter (61 stars, last pushed 3mo ago), licensed MIT. It adds 151 tokens to every session, about $0.0008 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
redis-vl-python CLAUDE.md
Instructions for redis/redis-vl-python, covering claude.md - redisvl project context, frequently used commands, development workflow, redis setup and documentation.
mcp-redis GEMINI.md
Instructions for redis/mcp-redis, covering redis mcp server extension, what this extension provides, available tools, string operations and hash operations.
RediSearch AGENTS.md
AGENTS.md instructions for RediSearch/RediSearch, covering redisearch development guide, proposing features and large changes, build commands, testing and header generation.
RediSearch CLAUDE.md
Claude Code instructions for RediSearch/RediSearch, a project described as: A query and indexing engine for Redis, providing secondary indexing, full-text search, vector similarity search and aggregations.
StateCore CLAUDE.md
Claude Code instructions for yul761/StateCore, covering statecore — claude context, what this is, commands, running locally and enable semantic retrieval (optional).
MCP-Nest CLAUDE.md
Instructions for rekog-labs/MCP-Nest, covering claude.md, what this repo is, packages, layout and commands.