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/cleberfarias/devscope-mcp/agents-mdgit clone --depth 1 https://github.com/cleberfarias/devscope-mcpWhat 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 | $0.00649 | $0.00649 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
devscope-mcp 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 yesterday.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevScope — instruções para agentes
O que é este repositório
Este é o monorepo da DevScope AI Platform. Ele reúne os componentes que juntos dão a agentes de IA contexto confiável sobre um projeto de software: documentação viva, especialistas de domínio (Skills) e ferramentas de execução (MCP).
Cada componente tem seu próprio AGENTS.md com regras específicas. Este arquivo cobre
apenas o que é válido para o repositório como um todo.
Estrutura
devscope/
├── AGENTS.md este arquivo
├── docs/
│ └── architecture/ desenho dos pilares, decisões e roadmap
├── skills/ conhecimento de domínio consultado pelo agente
└── mcp/
├── server/ servidor MCP read-only (AGENTS.md próprio em mcp/server/AGENTS.md)
├── auth/ permissão e auditoria para plugins (AGENTS.md em mcp/auth/AGENTS.md)
└── plugins/
└── chatguru/ primeiro plugin de execução (AGENTS.md em mcp/plugins/chatguru/AGENTS.md)
mcp/plugins/chatguru hoje tem uma única ação (get_service_health, leitura) —
existe para validar o mecanismo de registro de plugin, permissão e auditoria de ponta
a ponta, não como implementação completa do ChatGuru. Pastas restantes do roadmap
(rag/, ui/, sdk/) ainda não existem. Não crie stubs vazios para elas — cada uma
nasce quando sua fase começar, com conteúdo real desde o primeiro commit. Consulte
docs/architecture/overview.md para o roadmap completo antes de assumir que uma fase
futura já começou.
Regras obrigatórias
- Não adicionar pastas ou arquivos de fases futuras do roadmap sem decisão explícita
registrada em
docs/architecture/overview.md. - Toda Skill nova precisa ser conhecimento real e verificável, nunca um placeholder ("TODO", "em breve"). Se não há conteúdo genuíno para uma Skill ainda, ela não deve ser criada.
- Toda ação de qualquer plugin em
mcp/plugins/*que toque sistema externo (Docker, Kafka, Redis, Postgres, GitHub, Sentry, ChatGuru etc.) segue o modelo de permissão e auditoria definido em docs/architecture/permissions.md, implementado emmcp/auth. Nenhuma ação nova é aceita sem passar pelo checklist no final desse documento. - O componente
mcp/server/permanece somente leitura; suas regras próprias estão emmcp/server/AGENTS.mde têm precedência para qualquer mudança dentro dessa pasta.
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.
- yesterday First seen · 56 lines · 649 tokens per session scan A a1f6109612e5
devscope-mcp AGENTS.md is an instructions file published in the GitHub repository cleberfarias/devscope-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 649 tokens to every session, about $0.0032 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.