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.
npx agentmods add instructions/kubestellar/console/agents-mdgit clone --depth 1 https://github.com/kubestellar/consoleWhat 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 | $0.00940 | $0.00940 |
| Opus 5 | $0.00470 | $0.00470 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
console 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — KubeStellar Console
Tool-neutral entry point for AI coding agents (Claude Code, GitHub Copilot, Cursor, Codex, Aider, Continue, etc.) working on this repo.
Source of truth
All project conventions, architecture notes, critical rules, and testing requirements live in CLAUDE.md. That file is the canonical guide — read it first, and follow it regardless of which AI tool you are using.
Tool-specific overrides (if any):
- GitHub Copilot:
.github/copilot-instructions.md
If a tool-specific file conflicts with CLAUDE.md, CLAUDE.md wins.
Quick orientation
- Start the console:
./startup-oauth.sh(requires.envwith GitHub OAuth) or./start-dev.sh(mock user, no OAuth). - Ports: backend
8080, frontend5174, kc-agent WebSocket8585. - Pre-PR gate: Do not run
npm run buildornpm run lintlocally; CI validates both on the PR. - Testing is mandatory for UI and API work — see the "MANDATORY Testing Requirements" section in
CLAUDE.md.
Non-negotiable rules (excerpt — full list in CLAUDE.md)
- No magic numbers — use named constants.
- No hardcoded secrets — use env vars only.
- Array safety — guard with
(data || [])before.map/.filter/.join/for...of. - Use
DeduplicatedClusters()when iterating clusters. - All card data fetching goes through
useCache/useCached*hooks. - User-facing strings use
t()fromreact-i18next— never raw strings. - Netlify Functions (
web/netlify/functions/*.mts) must be updated alongside Go API handlers, since production (console.kubestellar.io) runs on Netlify, not the Go backend.
Reporting back
When you finish a task, summarize what changed and note that build/lint are validated by CI on the PR. Do not push or open PRs unless explicitly asked.
File-split refactor rules (oversized files — MANDATORY)
Splitting an oversized source or test file trips CI in predictable ways. Every split PR must follow these rules (learned from ten red split-PRs on 2026-08-26):
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.
- 2d ago First seen · 63 lines · 940 tokens per session scan A c6e3f1843e56
console AGENTS.md is an instructions file published in the GitHub repository kubestellar/console (130 stars, last pushed 2d ago), licensed Apache-2.0. It adds 940 tokens to every session, about $0.0047 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.
Other instructions, from other repositories
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit 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.
langchain 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.