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/rwx-cloud/skills/agents-mdgit clone --depth 1 https://github.com/rwx-cloud/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/rwx-cloud/skills/agents-md)<a href="https://agentmods.dev/instructions/rwx-cloud/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/rwx-cloud/skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.00449 | $0.00449 |
| Opus 5 | $0.00225 | $0.00225 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
skills 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 4d 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.
What it actually says
RWX Skills
Skills for working with RWX.
Requirements
The rwx CLI must be on your PATH. Install it from
RWX docs.
Available Skills
rwx
Generates or modifies an RWX CI/CD config by analyzing project structure,
selecting appropriate packages, and producing an optimized config with DAG
parallelism, content-based caching, and RWX packages. If an existing
.rwx/*.yml config is present, modifies it in place.
Usage: invoke with an optional description, e.g. "CI pipeline with tests and deploy" or "add a deploy step with secrets"
Migration Skills
migrate-from-gha
Migrates a GitHub Actions workflow to an optimized RWX config.
Usage: invoke with a path to a GitHub Actions workflow file, e.g.
.github/workflows/ci.yml
review-gha-migration
Reviews a generated RWX config against the original GitHub Actions workflow to catch semantic gaps, missing steps, and optimization opportunities.
Usage: invoke with a path to an RWX config file, e.g. .rwx/ci.yml
Validation
After writing or modifying RWX config files (.rwx/*.yml), validate them by
running:
rwx lint .rwx/<name>.yml
Skill Procedures
Full step-by-step procedures are in the skills/ directory:
skills/migrate-from-gha/SKILL.mdskills/review-gha-migration/SKILL.mdskills/rwx/SKILL.md
Each skill's SKILL.md includes rwx docs pull commands for fetching the latest
RWX documentation directly. Do NOT use WebFetch for these — use Bash to run
rwx docs pull and read stdout. When you need to find documentation beyond the
references listed in a skill procedure, use rwx docs search "<query>" to
discover the right page, then rwx docs pull to read it.
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.
- 4d ago First seen · 58 lines · 449 tokens per session scan A 6e7e2c0353be
skills AGENTS.md is an instructions file published in the GitHub repository rwx-cloud/skills (3 stars, last pushed 9d ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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
devopness CLAUDE.md
Claude Code instructions for devopness/devopness, a project described as: Devopness: AI DevOps on your cloud. Deploy apps, infra and CI/CD. Any cloud and any stack, one MCP. Deterministic API, opinionated and fully configurable. No cloud credentials in AI chats. Free plan.
zuke AGENTS.md
AGENTS.md instructions for zuke-build/zuke, covering agents.md, using zuke — the api, without guessing, tech stack, typescript 7 / tsgo and coding guidelines (non-negotiable).
docker-zoneminder CLAUDE.md
Instructions for jantman/docker-zoneminder, covering claude.md, project overview, build and test, ci/cd and architecture.
skills CLAUDE.md
Claude Code instructions for starslingdev/skills, covering starslingdev/skills, repository layout, working in this repo, opt-in debug logging (off by default) and registry audit triage (maintainers-only).
klaudiush CLAUDE.md
Claude Code instructions for smykla-skalski/klaudiush, covering claude.md, project overview, commands, completion (shell completion scripts) and doctor (diagnose setup and configuration).
everr AGENTS.md
AGENTS.md instructions for everr-labs/everr, covering constitution, web app packages/app, clickhouse, postgres and drizzle and everr cli.