Borrowing it
Nothing to install: this file belongs to martinambrus/haive. 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/martinambrus/haive/main/AGENTS.mdgit clone --depth 1 https://github.com/martinambrus/haiveWrote 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/martinambrus/haive/agents-md)<a href="https://agentmods.dev/instructions/martinambrus/haive/agents-md"><img src="https://agentmods.dev/badge/instructions/martinambrus/haive/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/martinambrus/haive/agents-md"><img src="https://agentmods.dev/badge/instructions/martinambrus/haive/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 | $0.07963 | $0.07963 |
| Opus 5.5 | $0.03185 | $0.03185 |
| Sonnet 5.5 | $0.01593 | $0.01593 |
| Haiku 4.5 | $0.00796 | $0.00796 |
Grade B, and why
haive AGENTS.md scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Host-side IO on a repository path goes through `@haive/shared/fs-safe`, never through a path-based `node:fs` call. The worker and the api run as root over trees that repositories and sandboxed agents write, so a path r Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- clawker (Apache 2.0 Go binary) wrapped via child_process in `sandbox/clawker-client.ts`. The binary is installed only when the worker image is built with `CLAWKER_RELEASE_URL` plus a matching `CLAWKER_SHA256`; nothing How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Haive
Deterministic multi-CLI workflow orchestration. Ports the legacy markdown-driven Claude Code workflow, autonomous /workflow loop and sandboxed environment replication to TypeScript steps and web forms. CLI agents handle only reasoning.
Ported legacy steps live in packages/worker/src/step-engine/steps/; their source archive is no longer vendored.
Stack
- pnpm workspace monorepo, turborepo
- Node 26, TypeScript 5.7, ES2024 target, NodeNext modules
- Hono 4 REST API on port 3001
- Next.js 16 + React 19 + Tailwind 4 web UI on port 3000
- Drizzle ORM on PostgreSQL 18, postgres.js driver
- BullMQ on Redis 8 (noeviction policy is required)
- Uploaded repo archives live in the
haive_reposnamed volume (shared by api and worker); Mailpit for dev SMTP - Docker Compose orchestrates everything; the dev stack is driven by
scripts/dev.sh(aliasedpnpm docker:dev), which wrapsdocker compose upwith the dev override and GPU layering - clawker (Apache 2.0 Go binary) wrapped via child_process in
sandbox/clawker-client.ts. The binary is installed only when the worker image is built withCLAWKER_RELEASE_URLplus a matchingCLAWKER_SHA256; nothing in this repo sets either, so the binary is absent from the shipped image and the wrapper is inert until someone wires it
Monorepo layout
haive/
package.json pnpm workspace root
pnpm-workspace.yaml
turbo.json
tsconfig.base.json
docker-compose.yml postgres, redis, mailpit, api, worker, web
docker-compose.dev.yml dev override: port exposure, hot reload, db-migrate one-shot
packages/
shared/ @haive/shared types, schemas, crypto, config, logger
database/ @haive/database Drizzle schema and migrations
api/ @haive/api Hono REST + WebSocket terminal proxy
worker/ @haive/worker BullMQ workers, step engine, sandbox manager, CLI adapters
web/ @haive/web Next.js Conductor-style UI
web-kit/ @haive/web-kit UI primitives and host contract shared by web and modules
tests/
e2e/ Playwright specs
fixtures/
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 Changed · +4 lines · -26 tokens per session b42be6953014
- 4d ago Changed · +4 lines · +39 tokens per session dda30c4b7b16
- 5d ago Changed · +4 tokens per session 033cf96ed0eb
- 12d ago Changed · +2 lines · +64 tokens per session fc69ed92b691
- 14d ago Changed · +4 lines · +48 tokens per session 2cbf9a053f68
- 15d ago Changed · +5 lines · +214 tokens per session 45f696ccac2f
- 16d ago Changed · +2 lines · +53 tokens per session 83b1f21ee0d4
- 17d ago Changed · +4 lines · +99 tokens per session 8b23dc839a25
- 18d ago Changed · +3 lines · +67 tokens per session 39e17736d9fe
- 19d ago First seen · 352 lines · 7,401 tokens per session scan B 44eb9193371e
haive AGENTS.md is an instructions file published in the GitHub repository martinambrus/haive (5 stars, last pushed 2d ago), licensed MIT. It adds 7,963 tokens to every session, about $0.0319 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.