Borrowing it
Nothing to install: this file belongs to Kong/ai-marketplace. 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/Kong/ai-marketplace/main/AGENTS.mdgit clone --depth 1 https://github.com/Kong/ai-marketplaceWrote 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/kong/ai-marketplace/agents-md)<a href="https://agentmods.dev/instructions/kong/ai-marketplace/agents-md"><img src="https://agentmods.dev/badge/instructions/kong/ai-marketplace/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/kong/ai-marketplace/agents-md"><img src="https://agentmods.dev/badge/instructions/kong/ai-marketplace/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 | $0.05629 | $0.05629 |
| Opus 5.5 | $0.02252 | $0.02252 |
| Sonnet 5.5 | $0.01126 | $0.01126 |
| Haiku 4.5 | $0.00563 | $0.00563 |
Grade A, and why
ai-marketplace 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 21d 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 — 655 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring Guide
This repo is for high-signal Kong skills. If you are using an LLM to add a new skill here, the main job is not to create more text. The job is to create a skill that helps an agent do Kong-specific work better than general model knowledge already would.
If your host environment exposes a built-in skill-authoring helper or skill such as skill-creator, build-a-skill, or similar, consult it before drafting or revising a skill. Use it to improve structure and calibration, then apply this repo's Kong-specific rules as the final authority. If the helper conflicts with this file, follow this file.
What Belongs Here
A skill in this repo should do at least one of these well:
- encode Kong-specific workflows that are easy to get wrong without guidance
- capture product or platform conventions that are not obvious from generic reasoning
- turn a broad request into a repeatable operating procedure
- point agents toward the right artifacts, constraints, or failure modes
Good examples:
- designing or debugging DataKit flows
- working with Konnect concepts, APIs, or configuration patterns
- handling Kong-specific deployment, gateway, plugin, or control-plane workflows
Weak examples:
- generic web research
- generic coding advice
- generic debugging advice that is not Kong-specific
If the skill would be equally useful in any repo, it probably does not belong here.
Before You Create A Skill
Before creating a new skill, check whether the repo already has one that should be extended instead.
- inspect
docs/skills.mdand the existingplugins/<plugin>/skills/trees before adding a new folder - extend an existing skill when the new request fits the same trigger class, same layer, and same operating procedure
- create a new skill only when the workflow, ownership boundary, or trigger surface is meaningfully different
- avoid near-duplicates with slightly different names or product wording
Useful decision rule:
- if the main difference is product surface, operator workflow, or diagnosis order, extend or create a domain skill
- if the main difference is config tool, file format, plan/apply workflow, or import/adoption path, extend or create a tool skill
- if both apply, keep diagnosis in the domain skill and hand off implementation to the tool skill
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.
- 21d ago Changed · +12 lines · +67 tokens per session 740c9e574f91
- 2mo ago First seen · 643 lines · 5,562 tokens per session scan A 08c95bc7ae18
ai-marketplace AGENTS.md is an instructions file published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. It adds 5,629 tokens to every session, about $0.0225 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 2026-08-31.
ai-marketplace AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-marketplace AGENTS.mdKong/ai-marketplace | Instructions file | 6 | 10d ago | MIT | A | 5,629 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |