agentmods.dev

flock AGENTS.md

Shared instructions for flock, a Go platform that runs groups of coding bots through coder, reviewer, and arbiter stages.

In plain words
What is it for?
Use them when changing bot roles, rendering agent instructions, running checks, or preparing repository work and pull requests.
Why use it?
They keep agent behavior, language, Git usage, and quality checks consistent across the platform.

Instructions file for CodexOpenCode

506 8d ago A scan 387 tokens original MIT
View the source file duckbugio/flock
Install

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.

agentmods
npx agentmods add instructions/duckbugio/flock/agents-md
Clone the repo
git clone --depth 1 https://github.com/duckbugio/flock

Made for: Codex, OpenCode.

Per session 387 This file is loaded in full into every session.
When invoked 387 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00387 $0.00387
Opus 5 $0.00193 $0.00193
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00039 $0.00039

Measured 2d ago against content hash 49cc966c2d7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flock 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 2d 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.

AGENTS.md · 14 lines

What it actually says

AGENTS.md

Канонические инструкции для ВСЕХ кодинг-агентов: Claude Code (через симлинк CLAUDE.md → AGENTS.md), Codex, Cursor, Gemini CLI и любых будущих.

flock — платформа автономных мульти-агентных ботов (Go), которую roost разворачивает на VPS пользователей. Боты работают циклами кодер→ревьювер→арбитр поверх agent.*-бэкендов (claude-code и др.).

  • Отвечай на русском; код, коммиты, PR и документация — на английском.
  • Без AI-соавторства: никаких Co-Authored-By: <ИИ> в коммитах и Generated with … в PR (для Claude Code продублировано в .claude/settings.json).
  • Не коммитить и не пушить без явной команды.
  • Перед началом любой работы — git fetch и сверка с origin/main: работа от устаревшей базы уже приводила к дублированию апстрим-фич.
  • Гейты: task default (tidy+fmt+lint+build), task lint, task tests (короткие — task tests:short), task security-scan.
  • Роли и промпты агентов ботов — core/agents/*.md (coder, reviewer, arbiter и др.); workspace-рендерер собирает из них CLAUDE.md и субагентов для ботов. Правки поведения ботов делаются в этих файлах и в рендерере, не «в рантайме».
  • PR-политика: один PR на задачу, фиксы ревью — коммитами в тот же PR.
Changes

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.

  1. 2d ago First seen · 14 lines · 387 tokens per session scan A 49cc966c2d7b

Subscribe to this mod's changes

flock AGENTS.md is an instructions file published in the GitHub repository duckbugio/flock (506 stars, last pushed 8d ago), licensed MIT. It adds 387 tokens to every session, about $0.0019 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 2026-08-30.

Autonomous Agentsai-agentanthropicchatbotclaudeclaude-code
Related

Other instructions, from other repositories

hermes-desktop AGENTS.md

Instructions for fathah/hermes-desktop, covering before starting work, post-task checklist (required — do not skip), what is lat.md?, commands and syntax primer.

fathah/hermes-desktop · 1,250 tokens

LobsterAI AGENTS.md

AGENTS.md instructions for netease-youdao/LobsterAI, covering agents.md, instruction scope, project snapshot, cowork vs openclaw and commands.

netease-youdao/LobsterAI · 4,886 tokens

hermes-desktop CLAUDE.md

Instructions for fathah/hermes-desktop, covering before starting work, post-task checklist (required — do not skip), what is lat.md?, commands and syntax primer.

fathah/hermes-desktop · 1,250 tokens

oneclaw CLAUDE.md

Instructions for 0xNyk/oneclaw, covering claude.md, build & development commands, architecture, core traits (the extension points) and adding a new implementation.

0xNyk/oneclaw · 1,694 tokens

progressive-agent CLAUDE.md

Instructions for Rayan55050/progressive-agent, covering progressive agent, что это, текущая фаза: v1.0.0 — open source release, стек and ключевые архитектурные решения.

Rayan55050/progressive-agent · 1,462 tokens

oneclaw AGENTS.md

Instructions for 0xNyk/oneclaw, covering agents.md, build & development, validation checklist, architecture and core traits.

0xNyk/oneclaw · 690 tokens