What is prd-reference?

A reference guide for prd2, a command-line tool that manages Rossum.ai configurations between environments. It explains the required project structure, configuration files, deployment commands, and safety rules.

Use it when pulling, editing, reviewing, or preparing Rossum.ai hooks, formulas, schemas, and deployments with prd2.

It helps avoid using the obsolete prd tool, editing generated files incorrectly, or changing remote environments without approval.

prd-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 prd-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/prd-reference/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/prd-reference)

Your own site

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

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 858 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00054	$0.00858
Opus 5.5	$0.00022	$0.00343
Sonnet 5.5	$0.00011	$0.00172
Haiku 4.5	$0.00005	$0.00086

Measured 27d ago against content hash 7bbc58ff16ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prd-reference scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If `prd2` complains about credentials, don't go hunting through `~/.prd2/credentials.yaml`, `~/.config/prd2/`, or `find ~` — that path has burned multiple sessions. Instead, ask the user for a curl-style token string fro

plugins/rossum-sa/skills/prd-reference/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

prd2 (Project Rossum Deploy) Reference

This skill provides a comprehensive reference for the prd2 deployment CLI used to manage Rossum.ai configurations across environments. For complete details, see reference.md.

Check the project's tool first. A project with rdc.toml at its root is managed by rdc, not prd2 — load rdc-reference and do not run any prd2 command there. prd2 projects are marked by prd_config.yaml.

IMPORTANT: Always use prd2 (v2). The original prd (v1) from the deployment-manager package is deprecated and should not be used. prd2 uses a different project structure, configuration format, and deployment model.

Safety Rules

Do not run prd2 push, prd2 deploy, or any Rossum write API call without explicit user approval. These commands modify remote environments. Always describe what you intend to push/deploy and wait for confirmation. prd2 pull (read-only) is fine without confirmation.

Edit local .py files, not JSON. When modifying hook code or formula logic, only edit the .py file. Never edit the code field in hook JSON or the formula property in schema.json — prd2 push syncs .py files into JSON automatically.

Getting a token quickly

If prd2 complains about credentials, don't go hunting through ~/.prd2/credentials.yaml, ~/.config/prd2/, or find ~ — that path has burned multiple sessions. Instead, ask the user for a curl-style token string from the Rossum UI ("Settings → API access") and call the MCP tool rossum_set_token with it. That sets the credentials for the MCP tools without touching the filesystem.

It does not reach prd2, and no environment variable bridges the two: the MCP server is a separate process that sets none, and prd2 reads no ROSSUM_* variable at all (verified against the installed deployment_manager package — only PRD2_CONCURRENCY and AWS_PROFILE). prd2 takes its token from the per-directory credentials.yaml and nowhere else. So the two are authenticated separately: rossum_set_token for the MCP tools, credentials.yaml for prd2. If prd2 reports bad credentials, that file is expired — ask the user for a fresh token; do not go looking for another store.

Read the full file on GitHub · 49 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 33 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 Changed · +2 lines 7bbc58ff16ef
1mo ago Changed · +2 lines af94a7093282
2mo ago First seen · 45 lines · 54 tokens per session scan A 4b2ad00a42bc

Subscribe to this mod's changes

prd-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 858 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DevOps and cloud

prd-reference next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
prd-referencerossumai/claude-marketplace	Skill	5	5d ago	MIT	A	54	Claude Code
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	316k	8d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code

prd-reference