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/hidream-ai/vivago-agent-cli/agents-mdgit clone --depth 1 https://github.com/HiDream-ai/vivago-agent-cliWrote 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/hidream-ai/vivago-agent-cli/agents-md)<a href="https://agentmods.dev/instructions/hidream-ai/vivago-agent-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/hidream-ai/vivago-agent-cli/agents-md.svg" alt="Measured on agentmods" 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 | $0.00831 | $0.00831 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
vivago-agent-cli 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 3d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
This repository contains the Go VivagoAgent CLI and the Codex/Claude Code plugin bundle.
Product boundary
- The host agent delegates coarse-grained work to VivagoAgent through the bundled Go CLI.
- Business MCP tools and internal skills stay behind VivagoAgent and are never exposed by this plugin.
- Conversation and turn history are owned by VivagoAgent. Local code may persist identifiers, cursors, and task states for recovery, but must not create a second transcript store.
- The default Go build targets overseas development;
-tags prodtargets overseas production. Do not add runtime environment switching or domestic/App fallbacks. - Login uses the dedicated
/agent/loginpage and a loopback Form POST callback. Authentication stays behind anAuthProviderboundary so standard OAuth can replace it later. - Hosted MCP and MCP Tasks/MRTR are later transport options, not public Beta dependencies.
Engineering rules
- Go 1.25.12 or newer. Python 3.11 or newer is used only for build, distribution, and official plugin validation tooling; install
requirements-dev.txtfor the validator. - Add or change tests before production behavior.
- Never print access tickets, refresh tokens, cookies, presigned URLs, or authorization headers.
- Machine-readable stdout is a compatibility contract. Diagnostics belong on stderr.
- Keep entrypoints and runtime assembly under
cmd/vivago-agent/. - Keep protocol mapping in
internal/client/, authentication ininternal/auth/, host-facing command handling ininternal/cli/, and compile-time profiles ininternal/config/. - Keep the installable Go plugin source under
plugin/. Generated binaries and assembled marketplaces do not belong on the source branch. - Update
docs/plans/2026-08-07-vivago-agent-cli-go-public-beta-design.mdwhen architectural decisions change. - Record user-visible changes as one Markdown fragment under
changelog.d/. - Maintain a privacy-safe requirement and decision summary under
historical_prompts/whenever the user confirms a new product requirement, changes product scope, or accepts an architectural decision. Do this as part of the same task before claiming completion; do not wait for a separate reminder. - Historical prompt records are curated summaries, not chat transcripts. Use one dated Markdown file per coherent requirement thread, update that file while the same thread is active, and include: background, user requirement, accepted decisions, and explicit non-goals. Do not copy credentials, account details, customer data, private URLs, tokens, project/conversation/turn IDs, local paths, or unrelated conversation.
- Before finishing a task, inspect the current change and either update the relevant
historical_prompts/record or confirm that the task introduced no new product requirement, scope change, or architectural decision. Avoid duplicate records when an existing file already covers the same decision.
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.
- 3d ago First seen · 52 lines · 831 tokens per session scan A fd55218fd25f
vivago-agent-cli AGENTS.md is an instructions file published in the GitHub repository HiDream-ai/vivago-agent-cli (5 stars, last pushed 14d ago), licensed Apache-2.0. It adds 831 tokens to every session, about $0.0042 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
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).
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.
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.