Borrowing it
Nothing to install: this file belongs to DeHor-Labs/transcreve-ai. 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/DeHor-Labs/transcreve-ai/main/AGENTS.mdgit clone --depth 1 https://github.com/DeHor-Labs/transcreve-aiWrote 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/dehor-labs/transcreve-ai/agents-md)<a href="https://agentmods.dev/instructions/dehor-labs/transcreve-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/dehor-labs/transcreve-ai/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/dehor-labs/transcreve-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/dehor-labs/transcreve-ai/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 | $0.00747 | $0.00747 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade C, and why
transcreve-ai AGENTS.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Para execucoes temporarias, limpe os artefatos ao final. Um padrao seguro e criar um diretorio dedicado com `mktemp -d`, usar `--out "$TMP/runs"` e `--index-db "$TMP/index.db"`, ler os arquivos necessarios e depois exe How it starts
The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TranscreveAI Agent Instructions
Escopo
Estas instrucoes sao o contrato minimo para qualquer IDE, agent ou assistente com LLM que opere neste repo.
Uso aninhado obrigatorio
- Sempre que um agente usar o TranscreveAI, trate a execucao como fluxo aninhado: mantenha
run_id,outeindex-dbidentificaveis para o agente chamador. - Existem dois modos de retencao:
- Temporario por padrao: quando o agente so precisa extrair/resumir/responder a partir de YouTube, Reels, TikTok, arquivo local etc., use
--oute--index-dbisolados em/tmpou cache temporario, leiaknowledge.md/analysis.json, responda ao usuario e limpe os artefatos brutos ao final. - Duravel somente quando pedido: preserve
knowledge.md,analysis.json, frames/audio/source e/ou indexe no indice real apenas quando o usuario pedir salvar, indexar, transformar em conhecimento consultavel, auditar evidencias depois, ou reutilizar o dossie em outro fluxo.
- Temporario por padrao: quando o agente so precisa extrair/resumir/responder a partir de YouTube, Reels, TikTok, arquivo local etc., use
- Quando a retencao duravel for pedida, rode
transcreveai share RUN_ID --jsondepois da analise. Se o run usou indice isolado, passe o mesmo--index-dbou usetranscreveai share --run-dir "$RUN_DIR" --json. O pacote gerado incluihandoff.md,manifest.json,knowledge.mdeanalysis.json, e atualizacatalog.json/index.mdno diretorio raiz de compartilhamento para outro agente descobrir e retomar sem depender de paths soltos. - Se o dossie for preservado ou indexado, informe explicitamente ao agente chamador:
O dossie que voce criou foi salvo para voce como conhecimento. - A mensagem de preservacao deve citar o caminho do
knowledge.md, orun_ide se o conhecimento ficou salvo no indice real do usuario ou em um indice isolado do agente. - Se o dossie foi usado de modo temporario e limpo, nao diga que ficou salvo; informe o
run_id, que a resposta foi baseada nos artefatos gerados, e que os temporarios foram removidos.
Regras operacionais
- Em smoke tests, demos e validacoes automatizadas, prefira
--index-db /tmp/...e--out /tmp/...para nao misturar provas com o indice real do usuario. - Quando o usuario pedir para usar o TranscreveAI, baseie a resposta nos artefatos gerados (
knowledge.md,analysis.jsone arquivos de template quando existirem), nao em um dossie paralelo manual. - Para execucoes temporarias, limpe os artefatos ao final. Um padrao seguro e criar um diretorio dedicado com
mktemp -d, usar--out "$TMP/runs"e--index-db "$TMP/index.db", ler os arquivos necessarios e depois executarrm -rf "$TMP". - Se a execucao temporaria usou o indice real por engano ou precisou registrar run no indice real, remova o run com
transcreveai runs rm RUN_ID --forceantes de apagar a pasta do run. - Nao exponha chaves, cookies ou URLs sensiveis completas em logs ou respostas.
- Mantenha os arquivos de instrucao para IDEs/agents sincronizados com este contrato.
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.
- 9d ago First seen · 26 lines · 747 tokens per session scan C cd9da28f1c7e
transcreve-ai AGENTS.md is an instructions file published in the GitHub repository DeHor-Labs/transcreve-ai (5 stars, last pushed yesterday), licensed MIT. It adds 747 tokens to every session, about $0.0037 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.