What is rdc-reference?

A reference guide for Rossum Deployment as Code, a command-line tool that stores an organisation's configuration as files and synchronises it with a remote service.

Use it to understand rdc project markers, read or reconcile environment configuration, and follow the safety rules for dry runs and approved synchronisation.

It helps identify which deployment tool owns a project and prevents using incompatible tools. It also explains that synchronisation can change the remote system and should first be previewed.

rdc-reference — Skill for Claude Code by rossumai/claude-marketplace

Install

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.

Any agent

npx skills add rossumai/claude-marketplace --skill rdc-reference

Clone the repo

git clone --depth 1 https://github.com/rossumai/claude-marketplace

Made for: Claude Code.

Or install rossum-sa, the plugin that ships this one along with the rest of its 35 skills, 4 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/rdc-reference/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/rdc-reference)

Your own site

<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/rdc-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/rdc-reference/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/rdc-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/rdc-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,317 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00192	$0.01317
Opus 5.5	$0.00077	$0.00527
Sonnet 5.5	$0.00038	$0.00263
Haiku 4.5	$0.00019	$0.00132

Measured 27d ago against content hash 22aa60241471, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rdc-reference 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 27d 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.

plugins/rossum-sa/skills/rdc-reference/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rdc (Rossum Deployment as Code) Reference

rdc is a single-binary CLI that mirrors a Rossum org's configuration as plain files under envs/<env>/ and reconciles them with the remote in one command. It replaces prd2's pull / push / deploy trio with sync and migrate. Full details in reference.md.

First: which tool owns this project?

Decide from the files, never from habit. The two trees are not interchangeable — running the wrong tool against a project corrupts its state or does nothing useful.

Marker at the project root	Tool	Load
`rdc.toml` + `envs/` + `.rdc/`	rdc	this pack
`prd_config.yaml` (+ `<org>/<subdir>/` dirs with `_[<id>]` file names)	prd2	`prd-reference`

Never run prd2 in an rdc project or rdc in a prd2 project. If both markers exist, ask the user which one is authoritative.

Safety rules

rdc sync <env> writes to the remote. Without flags it pulls and pushes. Treat it like prd2 push: run rdc sync <env> --dry-run first, show the plan, and wait for explicit approval before the real run.
Read-only against the remote: rdc sync <env> --dry-run, and rdc sync <env> --no-push (pulls remote changes into local files, never writes the org — the rdc equivalent of prd2 pull). Both are fine without asking; --no-push does rewrite local files, so check git status first.
Never pass --allow-deletes or --conflict keep-local / use-remote on your own. Deletes and conflict resolution each need the user's explicit say-so. --yes does not authorise deletes.
Follow the project's promotion chain. Typically dev → test → prod, one hop at a time, with no dev → prod. rdc won't stop a skipped stage, so check the project's README / CLAUDE.md before any rdc migrate, and ask when the chain isn't written down.
rdc migrate and rdc doctor make zero remote calls but rewrite local files — preview with --dry-run, review with git diff.
Claude's shell is non-TTY, so rdc behaves as if --yes were passed: conflicts fall back to shadow files (<file>.<env>), pending deletes make the sync refuse. Report those; do not resolve them silently.

Read the full file on GitHub · 48 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

reference.md 14 KB

Changes

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.

27d ago First seen · 48 lines · 192 tokens per session scan A 22aa60241471

Subscribe to this mod's changes

rdc-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 192 tokens to every session and 1,317 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-15.

Cloud DevOps and cloud

rdc-reference next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rdc-referencerossumai/claude-marketplace	Skill	5	5d ago	MIT	A	192	Claude Code
gke-compute-classesgoogle/skills	Skill	24k	today	Apache-2.0	A	83	Claude Code, Codex
gke-workload-securitygoogle/skills	Skill	24k	today	Apache-2.0	A	171	Claude Code, Codex
gke-reliabilitygoogle/skills	Skill	24k	today	Apache-2.0	A	85	Claude Code, Codex
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
cloud-architectJeffallan/claude-skills	Skill	12k	today	MIT	A	71	Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code