agentmods.dev

KBase AGENTS.md

A repository instruction file describing how to organize and use a knowledge base called KBase. The knowledge base stores verified references, notes, rules, workflows, environment settings, permissions, plans, and event hooks.

In plain words
What is it for?
Use it when working in KBase to bootstrap a session, locate project references or rules, add notes and workflows, manage plans, and understand the repository structure.
Why use it?
It gives agents a clear startup sequence and a consistent place to find project knowledge and operating rules. It also explains how folders and nested instruction files fit together.

Instructions file for CodexOpenCode

2 6mo ago A scan 257 tokens original MIT
View the source file hayabusa-cloud/KBase
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/hayabusa-cloud/kbase/agents-md
Clone the repo
git clone --depth 1 https://github.com/hayabusa-cloud/KBase

Made for: Codex, OpenCode.

Per session 257 This file is loaded in full into every session.
When invoked 257 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 $0.00257 $0.00257
Opus 5 $0.00129 $0.00129
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash 8376f372323f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

KBase 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 · 24 lines

What it actually says

AGENTS.md -- KBase

Read this file and ROOT/ at session start and after compaction.

Bootstrap

AGENTS.md → ROOT/AGENTS.md → ROOT/communication.md → ROOT/instructions.md

Structure

Dir Role Nesting
ROOT/ Meta-principles, bootstrap, commands —
refs/ Verified external knowledge <domain>/<topic>
notes/ Project insights and decisions <project>/<topic>
skills/ Automation workflows <tool> or <project>/<workflow>
rules/ Constraints and conventions <role>, <lang>, <project>
env/ Environment configurations <project>/<workflow>
perms/ Secrets and credentials (gitignored) <role> or <project>
hooks/ Event-driven callbacks <project>
plans/ Auto-generated task plans <project>/<yyyymm>/<issue>

Every level has AGENTS.md (guide) and INDEX.md (contents).

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 · 24 lines · 257 tokens per session scan A 8376f372323f

Subscribe to this mod's changes

KBase AGENTS.md is an instructions file published in the GitHub repository hayabusa-cloud/KBase (2 stars, last pushed 6mo ago), licensed MIT. It adds 257 tokens to every session, about $0.0013 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.

Memory and contextProductivityagenticagentic-workflowai-agentknowledge-management
Related

Other instructions, from other repositories

deer-flow copilot-instructions.md

Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.

bytedance/deer-flow · 1,714 tokens

toh-framework CLAUDE.md

Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.

wasintoh/toh-framework · 3,818 tokens

agentfactory CLAUDE.md

Claude Code instructions for stempeck/agentfactory, covering agentfactory, build commands, dependencies, project structure and cli commands.

stempeck/agentfactory · 1,786 tokens

mavericks-os CLAUDE.md

Claude Code instructions for yahor-punko/mavericks-os, covering claude.md, what this repo is, session start, operational commands and architecture.

yahor-punko/mavericks-os · 14,709 tokens

harikos.ai AGENTS.md

AGENTS.md instructions for ashyeager/harikos.ai, covering agents.md — harikos ai repository instructions, 1. read first, 2. product definition, 3. mvp means a real saas and 4. reality-only rule.

ashyeager/harikos.ai · 2,483 tokens

earnings-edge AGENTS.md

AGENTS.md instructions for suhaas/earnings-edge, covering earnings-edge: agent development guidelines, architecture & core concepts, the graph, agent roles and tools & skills boundary.

suhaas/earnings-edge · 4,591 tokens