specd: Instructions file for Claude Code

CLAUDE.md

specd CLAUDE.md is an instructions file for Claude Code from jnerytech/specd. It costs 1,750 tokens per session, scanned A, original, MIT.

A set of project instructions for working on specd, a TypeScript command-line tool for specification-driven development. It documents the project's rules, command behavior, architecture, and required locations for specifications.

In plain words
What is it for?
Use it when modifying specd to understand its principles, exit-code contract, verification gate, build commands, and specification conventions.
Why use it?
It gives a coding agent the repository's constraints so proposed changes do not violate its design or quality checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is jnerytech/specd's own configuration. It tells Claude Code how to work on specd 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 specd configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jnerytech/specd. 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/jnerytech/specd/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jnerytech/specd

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 specd CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jnerytech/specd/claude-md/github.svg)](https://agentmods.dev/instructions/jnerytech/specd/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jnerytech/specd/claude-md"><img src="https://agentmods.dev/badge/instructions/jnerytech/specd/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for specd CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jnerytech/specd/claude-md"><img src="https://agentmods.dev/badge/instructions/jnerytech/specd/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,750 This file is loaded in full into every session.
When invoked 1,750 The same file — it is already loaded in full.
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 $0.01750 $0.01750
Opus 5.5 $0.00700 $0.00700
Sonnet 5.5 $0.00350 $0.00350
Haiku 4.5 $0.00175 $0.00175

Measured 12d ago against content hash 60ddf42e4fb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

specd 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 12d 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.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specd — instruções para agentes

CLI de spec-driven development cujo diferencial é detecção de drift por âncoras: cada requisito declara onde é realizado no código, e o gate reprova quando a âncora deixa de resolver.

Pacote npm @jnerytech/specd, binário specd, TypeScript. Repositório público em github.com/jnerytech/specd. Para rodar do clone: npm install && npm run build, depois node dist/cli.js <comando> — ou npm link uma vez, e aí specd funciona como nos exemplos.

Princípios invioláveis

Estes não são preferências. Violá-los destrói a proposta de valor do produto. O porquê de cada um — assimetrias, instâncias reais, modos de falha — está em docs/principios.md; leia antes de propor mudança em qualquer princípio.

  • no-llm-in-decision-path — A CLI nunca chama LLM no caminho de decisão. Nenhum módulo alcançável a partir de verify() importa cliente de LLM; há teste de arquitetura. Determinismo protege o exit code, e a mesma disciplina se estende à escrita destrutiva em sistema de terceiro, que é irreversível.
  • single-gate — Um único gate. Só specd verify retorna 1 por reprovação de qualidade. Outros comandos retornam não-zero apenas por falha operacional.
  • gate-no-network — O gate nunca acessa a rede. explore e sync acessam; verify não. Há teste de arquitetura.
  • no-guessing-on-conflict — Nunca adivinhar em conflito. Âncora ambígua, conflito de merge e estado inconsistente saem com erro e diagnóstico. Jamais auto-resolução.
  • config-only-on-divergence — Botão de configuração só existe se dois clientes reais divergirem.
  • memory-is-ephemeral — Memória é efêmera; verdade durável vai para spec ou ADR.
  • anchor-necessary-not-sufficient — Âncora é necessária, nunca suficiente. Ela responde onde, não se nem quando. Nunca aponta para implementação parcial: âncora honestamente pendurada é preferível a resolvê-la para um stub.
  • absence-is-not-compliance — Ausência de dado não é conformidade. Verificou-e-certo, verificou-e-errado e não-consegui-verificar são três resultados; o terceiro nunca é verde. Vale nas duas direções: resposta de sucesso de sistema externo não é prova de que a escrita aconteceu — quem confirma é a releitura.
  • costly-ops-are-not-silent — Operação que custa alguma coisa não acontece em silêncio. Escrita destrutiva ou fora do repositório ou para e nomeia a escolha, ou deixa o resultado onde a revisão passa antes de virar história. O custo de uma operação é visível no momento em que é pago.

Read the full file on GitHub · 74 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. 12d ago First seen · 74 lines · 1,750 tokens per session scan A 60ddf42e4fb0

Subscribe to this mod's changes

specd CLAUDE.md is an instructions file published in the GitHub repository jnerytech/specd (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,750 tokens to every session, about $0.0070 per session on Opus 5.5. 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 2026-10-02.

Related

Other instructions, from other repositories