Borrowing it
Nothing to install: this file belongs to elzobrito/ESAA-Core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/elzobrito/ESAA-Core/main/AGENTS.mdgit clone --depth 1 https://github.com/elzobrito/ESAA-CoreWrote 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/elzobrito/esaa-core/agents-md)<a href="https://agentmods.dev/instructions/elzobrito/esaa-core/agents-md"><img src="https://agentmods.dev/badge/instructions/elzobrito/esaa-core/agents-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.
<a href="https://agentmods.dev/instructions/elzobrito/esaa-core/agents-md"><img src="https://agentmods.dev/badge/instructions/elzobrito/esaa-core/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01058 | $0.01058 |
| Opus 5.5 | $0.00423 | $0.00423 |
| Sonnet 5.5 | $0.00212 | $0.00212 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
ESAA-Core 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 2mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ESAA
O ESAA não usa MCP. Use python -m esaa, com --root apontando para este
workspace. O pacote Python é esaa-core; o módulo é esaa.
Autoridade e contexto
O Orchestrator é o único escritor do event store e dos efeitos finais.
AGENT_CONTRACT,
ORCHESTRATOR_CONTRACT,
schema do agente e
RUNTIME_POLICY definem as regras aplicáveis.
Não edite diretamente .roadmap/activity.jsonl nem suas projeções
(roadmap.json, issues.json, lessons.json, project_profile.json).
Para trabalhar numa tarefa, obtenha python -m esaa dispatch-context TASK-ID.
Use eligible para descobrir tarefas disponíveis e state TASK-ID para estado.
Leia somente as referências necessárias à tarefa; padrões de leitura autorizada
não são uma exigência de varrer o repositório. O contexto contém referências a
artefatos; recupere seu conteúdo quando necessário dentro dos limites autorizados.
Os perfis PARCER em .roadmap/ são orientação por papel, carregada sob demanda.
Trabalho e conclusão
Consultas e diagnósticos são somente leitura: não emita transições nem
file_updates. Relate o resultado e as limitações relevantes.
Na execução governada, claim e complete são submissões separadas. Cada envelope
contém uma activity_event e prior_status coerente. JSON puro é obrigatório no
envelope submetido ao Orchestrator, não nas mensagens de conversa.
O actor que reivindicou completa; file_updates só acompanha complete.
A revisão segue o papel autorizado e a política ativa. done é terminal:
problemas exigem issue.report e o fluxo de hotfix, sem reabrir a tarefa original.
Investigue contexto recuperável e resolva escolhas locais reversíveis dentro do
escopo autorizado sem pedir aprovação a cada passo. Prepare e valide candidatos
em ambiente permitido; os efeitos finais continuam via file_updates.
Quando a tarefa incluir execução, inspeção e correção, prossiga até satisfazer os
critérios de aceitação e reúna verificações reais antes de complete.
Respeite os mínimos de checks do contrato; complete não é aprovação nem publicação.
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.
- 2mo ago Changed · -166 lines · -1,096 tokens per session 00fbb7069383
- 2mo ago First seen · 243 lines · 2,154 tokens per session scan A 9398d6317000
ESAA-Core AGENTS.md is an instructions file published in the GitHub repository elzobrito/ESAA-Core (67 stars, last pushed 4d ago), licensed MIT. It adds 1,058 tokens to every session, about $0.0042 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 2026-08-30.
ESAA-Core AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ESAA-Core AGENTS.mdelzobrito/ESAA-Core | Instructions file | 67 | 4d ago | MIT | A | 1,058 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |