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/davidomil/cloudx/agents-mdgit clone --depth 1 https://github.com/davidomil/cloudxWhat 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 | $0.01129 | $0.01129 |
| Opus 5 | $0.00564 | $0.00564 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
cloudx 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 yesterday.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloudX Repository Instructions
Purpose
CloudX is a local-first workbench that can control terminals, files, Codex sessions, automation, ASR, and a documentation archive on the host machine. Treat changes as workstation-control software, not as a conventional public web application.
Read this file before making a change. Then read the nearest scoped AGENTS.md
for every path in scope. Scoped files add module rules; they do not replace this
contract.
Sources Of Truth
docs/architecture/system-context.md: runtime processes and trust boundaries.docs/architecture/module-ownership.md: authoritative module owners and dependency direction.docs/architecture/state-invariants.md: state and lifecycle rules.docs/architecture/testing-map.md: required evidence by changed area..agents/pr-review-policy.toml: machine authority for path classification, risk, selected review skills, checks, human review, and automerge eligibility..agents/schemas/: typed handoffs between planning, implementation, verification, review, and merge authorization.docs/AI_CHANGE_PROCESS.md: end-to-end repository change process.
Do not duplicate machine policy in prose. When policy and prose disagree, stop and correct the inconsistency through a human-reviewed agent-policy change.
Required Change Process
For every non-trivial change, use $change-orchestrator:
- Classify the exact changed paths with
.agents/pr-review-policy.toml. - Create a
.agents/schemas/plan.schema.jsonartifact in a fresh planning context. - Review the plan in a different fresh context with
$review-plan. - Implement only a clean plan with
$implement-change. - Run deterministic, read-only verification with
$verify-change. - Run
$review-changeand every policy-selected area reviewer in fresh contexts. - Route findings back through implementation, verification, and review until clean. An iteration ceiling blocks the change; it never permits a bypass.
- Use
$review-prfor current-head PR review. Only$ship-changemay perform interactive or model-directed GitHub mutations. External Publisher and Merge controllers may perform only the deterministic operations granted to their separate GitHub App identities.
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.
- yesterday First seen · 116 lines · 1,129 tokens per session scan A 298c3004b10c
cloudx AGENTS.md is an instructions file published in the GitHub repository davidomil/cloudx (1 stars, last pushed 8d ago), licensed MIT. It adds 1,129 tokens to every session, about $0.0056 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
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
dev-flow AGENTS.md
Instructions for daphnee-ovo/dev-flow, covering dev-flow plugin, language policy, 注意事项, 命令 and 流程.
agentic-voice AGENTS.md
AGENTS.md instructions for maxanatsko/agentic-voice, covering agent guidelines, purpose, engineering principles, separation of concerns and kiss.
dev-flow CLAUDE.md
Instructions for daphnee-ovo/dev-flow, a project described as: Engineering discipline for AI coding agents — from requirements through delivery.
ai-driven-development AGENTS.md
Instructions for CodeAlive-AI/ai-driven-development, covering ai-driven development — development guide, git publishing defaults, when to create tags and releases, requires a new tag/release and does not require a new tag/release.
roamcode AGENTS.md
Instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.