Borrowing it
Nothing to install: this file belongs to intertwine/hive-orchestrator. 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/intertwine/hive-orchestrator/main/AGENTS.mdgit clone --depth 1 https://github.com/intertwine/hive-orchestratorWrote 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/intertwine/hive-orchestrator/agents-md)<a href="https://agentmods.dev/instructions/intertwine/hive-orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/intertwine/hive-orchestrator/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/intertwine/hive-orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/intertwine/hive-orchestrator/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 | $0.01086 | $0.01086 |
| Opus 5.5 | $0.00434 | $0.00434 |
| Sonnet 5.5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
hive-orchestrator 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unmaintained legacy software (final release 2.4.1, September 6, 2026). The guidance below is historical and is not authority to restart development, merge the unmerged branches, or publish another version. See
docs/legacy-closeout.md.
AGENTS
Hive is a v2-first repository.
Start with the hive CLI, not ad hoc markdown edits or compatibility shims.
First Steps
Read skills/hive-essentials/SKILL.md before doing anything else. It explains what Hive is, how entities relate, and the key conventions.
Working Rules
- If you are just using Hive, prefer an installed
hiveCLI in a clean workspace. Checkout-only helpers in this repo are for maintainers. - Treat
.hive/tasks/*.mdas the canonical task database. - Treat
projects/*/AGENCY.mdas the narrative project document. - Read
projects/*/PROGRAM.mdbefore autonomous edits or evaluator runs. - If repo-local docs, skills, memory, and current git state disagree, trust current repo state and tests first, then repo-local docs and
PROGRAM.md. - Keep the status doc for the release line you touch current (
docs/V2_*_STATUS.md). - Before substantial repo work, prefer
make workspace-status, or checkgit status --short,git worktree list,gh pr status, andhive doctor --jsondirectly. - In a fresh maintainer worktree, run
uv sync --extra devbeforepytestormake checkso the test-only dependencies are actually installed. - Build startup context with
hive context startup --project <project-id> --task <task-id> --json. - Use
make session PROJECT=<project-id>only from a repo checkout when you want a saved context file. - After task, run, or memory changes, refresh projections with
hive sync projections --json. - Use
hive driver doctor <driver>andhive sandbox doctor <backend>when debugging runtime or sandbox behavior. - Run validation appropriate to the changed surface. Use focused tests for narrow changes and
make checkfor broad Python/runtime changes or required release/merge gates. For documentation-only changes, check affected links, examples, or relevant documentation tests. If your slice touchesfrontend/console/**, console CI wiring, or packaged console validation, runmake console-checkbefore review. - If you request Claude review, treat it as pending until GitHub shows a new Claude comment or review artifact on the latest PR head. An
eyesreaction alone does not count as completion. - For maintainer-critical PRs, local Claude review is an acceptable primary or fallback review path when GitHub-managed review is delayed or ambiguous. The built-in
claude -p "/review <pr-number>"flow works well for this. Summarize the resulting findings in the PR thread. - After merging, watch the
pushCI run onmain. A red merge commit is new blocking work, even if the PR checks were green.
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.
- 1mo ago Changed · +4 lines · +38 tokens per session 5180d955f437
- 1mo ago Changed · +37 tokens per session ee79d42cf29e
- 1mo ago First seen · 76 lines · 1,011 tokens per session scan A 5cf926259956
hive-orchestrator AGENTS.md is an instructions file published in the GitHub repository intertwine/hive-orchestrator (22 stars, last pushed 1mo ago), licensed MIT. It adds 1,086 tokens to every session, about $0.0043 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.
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.
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.
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).