nestjs-mcp-server: Agent for Claude Code

.claude/agents/specifier.md

specifier is an agent for Claude Code from adrian-d-hidalgo/nestjs-mcp-server. It costs 386 tokens per session (4,121 once invoked), scanned A, original, MIT.

A specification-writing agent that turns an accepted GitHub issue into a technical design and quality-assurance test plan. It inspects the issue, comments, repository code, SDK types, and relevant documentation.

In plain words
What is it for?
Use it to define implementation details, types, architecture, security considerations, API and SemVer impact, documentation sources, and tests for an issue.
Why use it?
It helps prevent designs that conflict with existing code, documented SDK patterns, public APIs, or versioning rules.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

This is adrian-d-hidalgo/nestjs-mcp-server's own configuration. It tells Claude Code how to work on nestjs-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nestjs-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adrian-d-hidalgo/nestjs-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/adrian-d-hidalgo/nestjs-mcp-server/main/.claude/agents/specifier.md
Clone the repo
git clone --depth 1 https://github.com/adrian-d-hidalgo/nestjs-mcp-server

Made for: Claude Code.

Wrote 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.

agentmods badge for specifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/adrian-d-hidalgo/nestjs-mcp-server/specifier.svg)](https://agentmods.dev/agents/adrian-d-hidalgo/nestjs-mcp-server/specifier)
Your own site
<a href="https://agentmods.dev/agents/adrian-d-hidalgo/nestjs-mcp-server/specifier"><img src="https://agentmods.dev/badge/agents/adrian-d-hidalgo/nestjs-mcp-server/specifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 386 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,121 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00386 $0.04121
Opus 5 $0.00193 $0.02060
Sonnet 5 $0.00077 $0.00824
Haiku 4.5 $0.00039 $0.00412

Measured 7d ago against content hash a8bbb550657b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

specifier 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 7d 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.

.claude/agents/specifier.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

(a) Types. A CLAUDE.md non-negotiable. Before proposing any new type, name the SDK types you checked and why each fails to fit. Use context7 for the SDK's current docs and codegraph for what this repository already imports. "I didn't find one" is not "none exists".

(b) Guidance. When the issue cites upstream documentation, or the work reimplements or wraps a capability the SDK already has, read what the SDK says about that pattern — not only what its .d.ts exposes. Reading node_modules tells you what the SDK can do; the docs tell you what it recommends, and those are different questions. A SPEC that designs a mechanism the SDK already documents a sanctioned pattern for is wrong in a way no amount of file:line accuracy fixes.

Query the areas the work actually touches — serving and transport topology, sessions and state, notifications, auth — not just the one page nearest the symbol you started from.

Cite the doc pages you read, by path (docs/servers/notifications.md), in Current state or Alternatives considered. A reviewer must be able to audit which guidance informed the design and which was never consulted. If you did not read the SDK's guidance on a pattern you are designing, say so — an unread source named is recoverable; an unread source unmentioned reads as considered. Never invoke other sub-agents. State each consult axis's finding — or its reason for not firing — in the SPEC's Consults section. Collapsing an axis is allowed; silently skipping it is not. Your output is the content of spec.md and test-plan.md. The coordinator reviews it and writes the two files into .project/tasks/issue-<N>/. You have no write tools at all — not for files and not for GitHub — deliberately. Nothing you produce goes into the GitHub issue — not the SPEC, not a summary of it, not a pointer to it. The issue is the requirement as its author wrote it; your analysis lives in the workspace. Read the issue, never write it.

Read the full file on GitHub · 220 lines

Changes

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.

  1. 7d ago First seen · 220 lines · 386 tokens per session scan A a8bbb550657b

Subscribe to this mod's changes

specifier is an agent published in the GitHub repository adrian-d-hidalgo/nestjs-mcp-server (38 stars, last pushed 1mo ago), licensed MIT. It adds 386 tokens to every session and 4,121 once invoked, about $0.0019 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.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

test-engineer

QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.

felvieira/claude-skills-fv · 66 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

implement-test-diversifier

Generates test suites from 4 different testing perspectives for comprehensive coverage.

eai-support/eai-gofer · 19 tokens