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/xonovex/platform/agents-mdgit clone --depth 1 https://github.com/xonovex/platformWhat 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 | $0.01201 | $0.01201 |
| Opus 5 | $0.00600 | $0.00600 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
platform 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xonovex Platform Monorepo
Structure
Packages
agent: Agent CLI (agent-cli-go, five per-platform binary packages,agent-cli-go-github),agent-operator-go+ imageasset: Diagrams and images; private, pinned0.0.0, outside the lockstep release linecommand: Slash commands (command-utility,command-workflow); lockstep with the skill plugins and.claude-plugin/marketplace.jsonconfig: Shared ESLint, Prettier, TypeScript, Vite, Vitest configmoon: moonrepo nix plugins (moon-nix-toolchain,moon-nix-extension,moon-nix-runtime), versioned fromCargo.tomlscript: moon task binariesmoon-<domain>-<action>-<subject>; no binary means shared code (script-moon-common)shared: TypeScript (shared-core) and Go (shared-core-go,shared-agent-go) librariesskill: Agent skills catalog (skill-*)
Workflow
- Setup:
npm install - Tasks:
npx moon run <project>:<task>ornpx moon run #<tag>:<task> - Query:
moon query projects --tags "<pattern>" - Moon: a
moon.ymltag<name>inherits.moon/tasks/tag-<name>.yml;extendsrefines one (tag-typescript-script.yml,tag-typescript-config.yml->tag-typescript.yml). A redefined task replaces the parent'sdeps, so restate every inherited dep or setmergeDeps: replace - Dependencies: internal
@xonovex/*exact, a config package pins its plugins exactly, everything else caret. An exact pin elsewhere records its reason:typescriptandvitein.ncurc.cjs,@moonrepo/clibecause it resolves every task - Git: no feature branches or pushes unless asked
- Commits: conventional. Rebuild a restructured series on a temporary branch, confirm
git diff <old tip> <new tip>is empty before moving the branch, and verify each commit withnpx moon run :ci-check --forceso the series stays bisectable - Release: reviewed
version packagesPR only; merging tomainruns.github/workflows/release.yml(:ci-publish-> release/tag). Never bypass branch protection - Delegation: subagents only for large independent work such as a wide multi-file investigation; never to check your own work, and few
- Scope: deliver what the task asks; ask only when two readings mean materially different work. Flag a mistaken request in one sentence, then finish the whole task
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 · 56 lines · 1,201 tokens per session scan A 81bd4e69ee5b
platform AGENTS.md is an instructions file published in the GitHub repository xonovex/platform (5 stars, last pushed 2d ago), licensed MIT. It adds 1,201 tokens to every session, about $0.0060 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.
Other instructions, from other repositories
mcp-python-exec-sandbox CLAUDE.md
Claude Code instructions for lu-zhengda/mcp-python-exec-sandbox, covering claude.md, project, stack, structure and commands.
appwrite AGENTS.md
Instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, mandatory development principles and sow system.
selfhost-ai CLAUDE.md
Instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
SForum AGENTS.md
Instructions for zhuchunshu/SForum, covering agent guide, project intent, working principles, stack and directory map and commands.
redd-archiver CLAUDE.md
Instructions for 19-84/redd-archiver, covering claude.md, project overview, deviations from global standards, build & run commands and docker development (primary method).