Borrowing it
Nothing to install: this file belongs to exasol-labs/exasol-agent-skills. 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/exasol-labs/exasol-agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/exasol-labs/exasol-agent-skillsWrote 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/exasol-labs/exasol-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/exasol-labs/exasol-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/exasol-labs/exasol-agent-skills/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/exasol-labs/exasol-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/exasol-labs/exasol-agent-skills/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 | $0.04234 | $0.04234 |
| Opus 5 | $0.02117 | $0.02117 |
| Sonnet 5 | $0.00847 | $0.00847 |
| Haiku 4.5 | $0.00423 | $0.00423 |
Grade C, and why
exasol-agent-skills AGENTS.md scanned grade C with 2 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| `piped-interactive-codex` | Verifies that `curl ... | sh` reads agent and Codex skill selections from the controlling terminal | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Installer (`install.sh`)** — curl-pipeable, idempotent, POSIX shell (no bash, no jq). Supports both agents: How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
What This Repo Is
A skills marketplace for AI coding agents (Claude Code and OpenAI Codex) that gives them expertise in Exasol databases — guided Exasol Personal setup (local on macOS or AWS/Azure/Exoscale/STACKIT), exapump CLI, Exasol SQL, UDFs, BucketFS, cloud data loading, virtual schemas, and custom virtual schema adapter development.
Architecture
Plugin hierarchy: marketplace → plugin → skills + commands → references
.claude-plugin/marketplace.json— discovery entry point; lists plugins with versionplugins/exasol/.claude-plugin/plugin.json— plugin metadata; version must match marketplaceplugins/exasol/skills/exasol/SKILL.md— top-level router skill; public user model is/exasol <task>or natural-language Exasol requestsplugins/exasol/skills/*/SKILL.md— specialized skills with routing algorithms that load only the reference files relevant to the task (progressive disclosure). Skills:exasol(top-level router),exasol-setup-personal(guided local-or-cloud deployment that defers to the upstreamexasol/exasol-personaldocs),exasol-database(SQL/exapump),exasol-import(native IMPORT and exapump file movement into Exasol),exasol-export(native EXPORT and exapump file movement out of Exasol),exasol-cloud-storage-extension(Cloud Storage Extension import/export workflows),exasol-jdbc-virtual-schemas(JDBC/database-source virtual schema workflows),exasol-document-virtual-schemas(document-file virtual schema workflows for S3/GCS/Azure object storage),exasol-virtual-schema-adapter-development(custom virtual schema adapter build, packaging, and debugging workflows),exasol-extension-catalog(tool and architecture selection),exasol-distributed-ml(distributed ML and GPU workflows),exasol-udfs(UDFs/SLCs),exasol-bucketfs(BucketFS),exasol-notebook-connector-config(notebook-connector configuration),exasol-itde(local Docker Exasol lifecycle),exasol-notebook-connections(Python connection helpers),exasol-text-ai(Text AI Extension),exasol-transformers(Transformers Extension)plugins/exasol/commands/*.md— thin Claude-only/exasoland/bucketfsentry points that delegate to the shared router./bucketfsexists because BucketFS is the one Exasol task users repeat in a shell-like rhythm — list, upload, delete — where a short command earns itself; it is a typing shortcut, not a separate capability, and import and export earn the same only if they ever acquire that rhythm. The reasoning lives here and not in the command file, which ships — see Shapeplugins/exasol/skills/*/references/*.md— detailed docs loaded on-demand by SKILL.md routingplugins/exasol/skills/_template/— contributor skeleton, not a skill; it shipsSKILL.md.templateso that nothing discovers it as one
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.
- 5d ago Changed · +26 lines · +403 tokens per session 6bb2cfdff4f5
- 6d ago Changed · +122 lines · +1,657 tokens per session e15c7131dd91
- 10d ago First seen · 148 lines · 2,174 tokens per session scan C 6a98006b7f12
exasol-agent-skills AGENTS.md is an instructions file published in the GitHub repository exasol-labs/exasol-agent-skills (10 stars, last pushed 6d ago), licensed MIT. It adds 4,234 tokens to every session, about $0.0212 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.