ping-orchestration

A skill for designing and building authentication flows, which are step-by-step login or verification processes, across Ping Identity products. It covers journeys for login, registration, recovery, multi-factor authentication, passwordless access, and social sign-in.

In plain words
What is it for?
Use it to plan or create login, registration, recovery, MFA, step-up, passkey, magic-link, biometric, social-login, and scripted decision flows.
Why use it?
It helps turn an authentication goal into the right sequence of checks, decisions, branches, and user steps. It also accounts for differences between Ping platforms and can build supported flows directly.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/pingidentity/agent-plugins/ping-orchestration
Any agent
npx skills add pingidentity/agent-plugins --skill ping-orchestration
Clone the repo
git clone --depth 1 https://github.com/pingidentity/agent-plugins

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,509 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.01509
Opus 5 $0.00039 $0.00754
Sonnet 5 $0.00016 $0.00302
Haiku 4.5 $0.00008 $0.00151

Measured 2d ago against content hash 914cb5567a29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ping-orchestration 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.

plugins/ping-identity/skills/ping-orchestration/SKILL.md · 116 lines

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.

ping-orchestration

Design and build authentication flows, orchestration logic, and journey-based experiences across Ping Identity platforms. MCP tools handle execution; this skill supplies design patterns, node sequencing, branching logic, and platform-specific constraints.

What this skill does for you: Builds journeys and flows directly through MCP tools where they exist (AIC journeys); where a tool does not exist, it guides you through the design with node sequencing, branching logic, and platform constraints. Both modes are available — it uses whichever the platform supports for the task.

Invocation

Invoke this skill explicitly with /ping-orchestration or by saying "use ping-orchestration to...".

When to use this skill

Trigger on ANY question — including advisory, planning, and "what nodes do I need" requests, not just implementation — when the task involves:

  • Building or designing a login, registration, recovery, MFA, or step-up journey in PingOne Advanced Identity Cloud (AIC) / PingAM
  • Passwordless authentication flows (passkeys, FIDO2, magic links, biometric)
  • Authenticator app login, push MFA, or TOTP enrollment flows
  • Transaction approvals via email or push (CIBA / out-of-band step-up)
  • Creating or designing a DaVinci flow for authentication, MFA, or orchestration
  • Configuring a PingAM authentication tree or scripted decision node
  • Planning or reviewing journey structure before implementation
  • Deciding between inner journeys, scripted nodes, or DaVinci connectors
  • Any question about designing, planning, or advising on authentication flows, journeys, or orchestration logic in PingOne Advanced Identity Cloud (AIC), PingOne / DaVinci, or PingAM

When NOT to use this skill

  • If the platform is not yet set up (no tenant, no realm, no app registered): use ping-foundation first
  • If the task is configuring the platform layer (apps, directories, policies, branding): use ping-foundation
  • If the task is invoking a Universal Service (Protect, Verify, IGA, Credentials) without needing flow design: use ping-universal-services
  • If the task is integrating the flow into an app or SDK: use ping-app-integration
  • If unsure which platform: use ping-quickstart first

Read the full file on GitHub · 116 lines

Files

What ships with it

25 files 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.

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.

  1. 2d ago First seen · 116 lines · 79 tokens per session scan A 914cb5567a29

Subscribe to this mod's changes

ping-orchestration is a skill published in the GitHub repository pingidentity/agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,509 once invoked, about $0.0004 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.