kagent is a Kubernetes-native framework for building, deploying, and managing AI agents as Kubernetes resources. It is intended for teams operating agents and tools alongside Kubernetes workloads, with catalogue entries supporting its agent-management workflows.
Borrowing it
Nothing to install: this file belongs to kagent-dev/kagent. 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/kagent-dev/kagent/main/AGENTS.mdgit clone --depth 1 https://github.com/kagent-dev/kagentWrote 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/kagent-dev/kagent/agents-md)<a href="https://agentmods.dev/instructions/kagent-dev/kagent/agents-md"><img src="https://agentmods.dev/badge/instructions/kagent-dev/kagent/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/kagent-dev/kagent/agents-md"><img src="https://agentmods.dev/badge/instructions/kagent-dev/kagent/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 | $0.02000 | $0.02000 |
| Opus 5.5 | $0.00800 | $0.00800 |
| Sonnet 5.5 | $0.00400 | $0.00400 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
kagent 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.
This is a copy
100% identical to skills AGENTS.md — 137 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kagent Development Guide
This file defines the repository-wide rules for agents working on kagent. Read the code in scope before changing it. For detailed development and CI workflows, use the kagent-dev skill. See STYLE.md for language-specific conventions.
AGENTS.md is the canonical repository instruction filename. Before editing a
file, read every applicable nested AGENTS.md along its directory path, even when
starting from the repository root. Nested guidance adds directory-specific rules;
the shared architecture and component boundaries below still apply.
1. Current Architecture
Kagent is a Kubernetes-native control plane for defining, running, and invoking AI agents.
Agent,Harness, andAgentTemplateareapi.kagent.dev/v1alpha3Kubernetes APIs. Agent composes inline or referenced behavior with a referenced Harness. AgentTemplate is reusable behavior; Harness is platform-managed runtime policy.Sessionis PostgreSQL-backed control-plane state exposed through gRPC. It is not a Kubernetes resource.- Upstream A2A owns task, interaction, streaming, and history semantics. Do not create parallel session or task models.
- Substrate Actors are the compute backend. Durable directories own private runtime state that must survive actor replacement.
- Harness compilers translate resolved templates into backend inputs. Keep compilation separate from applying those inputs.
- The public API describes agent behavior, not infrastructure mechanics. Do not expose Kubernetes scheduling, service accounts, arbitrary containers, channels, profiles, or generic extension maps.
The release-blocking harnesses are kagent, Codex, and Claude. Prefer clean-install behavior over compatibility with legacy session-backed agents unless compatibility is explicitly required.
2. Sources of Truth
- Current architecture is documented in docs/architecture.
- Development workflows and current architecture notes are in .agents/skills/kagent-dev/SKILL.md.
.agents/skills/is the source of truth for repository skills. Keep one relative per-skill symlink under.claude/skills/for Claude Code; do not symlink the whole directory.- General and language-specific conventions are in STYLE.md.
- Generated code is never the source of truth. Change the API, protobuf, SQL, or schema source and regenerate its outputs.
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 · +3 lines · +60 tokens per session 11ede12b03df
- 22d ago Changed · +3 lines · +46 tokens per session e007aeb64a47
- 25d ago Changed · +2 tokens per session 32bb847db765
- 28d ago Changed · +1 tokens per session a78fcd36e679
- 1mo ago Changed · -1 lines · -57 tokens per session cbee0ef608db
- 1mo ago Changed · +130 lines · +1,944 tokens per session 2c2ad52b28ba
- 2mo ago First seen · 1 lines · 4 tokens per session scan A 6ebdb617a810
kagent AGENTS.md is an instructions file published in the GitHub repository kagent-dev/kagent (4,165 stars, last pushed today), licensed Apache-2.0. It adds 2,000 tokens to every session, about $0.0080 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to skills AGENTS.md, differing in 137 lines, and is treated as a copy.
kagent AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kagent AGENTS.mdkagent-dev/kagent | Instructions file | 4.2k | today | Apache-2.0 | A | 2,000 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |