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 skills/pingidentity/agent-plugins/ping-foundationnpx skills add pingidentity/agent-plugins --skill ping-foundationgit clone --depth 1 https://github.com/pingidentity/agent-pluginsWhat 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 | $0.00109 | $0.01705 |
| Opus 5 | $0.00055 | $0.00852 |
| Sonnet 5 | $0.00022 | $0.00341 |
| Haiku 4.5 | $0.00011 | $0.00170 |
Grade A, and why
ping-foundation 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ping-foundation
Platform setup, administration, and core configuration for all Ping Identity deployments. Covers tenant and environment setup, apps, directories, policies, branding, and on-premises software administration. MCP tools handle execution; this skill supplies architecture patterns, sequencing, configuration constraints, and guardrails.
What this skill does for you: Generates configuration and drives setup directly through MCP tools where they exist (PingOne, AIC); where a tool does not exist, it guides you through the docs with the correct sequencing, field constraints, and guardrails. Both modes are available — it uses whichever the platform supports for the task.
Invocation
Invoke explicitly with /ping-foundation or by saying "use ping-foundation to...".
When to use this skill
Trigger on ANY question about setting up, configuring, administering, or planning a Ping Identity platform — including advisory and planning requests:
- Set up or provision environments, tenants, or realms
- Register OIDC, SAML, WS-Federation, or OAuth 2.0 applications
- Configure SSO, Platform SSO, or workforce single sign-on
- Manage directories, identity stores, or user populations
- Configure authentication policies, sign-on policies, or branding
- Administer PingFederate, PingAccess, PingDirectory, or PingID
- Deploy or upgrade on-premises Ping software
- Automate configuration with Ping CLI (
pingcli), export Terraform/CaC packages, or manage multi-environment promotion pipelines - Advisory: "How should I structure my tenant?", "What client type should I use?"
When NOT to use this skill
- If the primary task is designing a DaVinci flow or PingOne Advanced Identity Cloud journey: use
ping-orchestration - If the task is configuring a Universal Service (Protect, Verify, IGA, Credentials) as a standalone service: use
ping-universal-services. If the task is wiring a Universal Service into a journey or DaVinci flow (e.g., adding Verify to a registration journey): useping-orchestration - If the task is integrating Ping into an app or SDK: use
ping-app-integration - If unsure which platform: use
ping-quickstartfirst
What ships with it
23 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.
- ping-marketplace.json 1.2 KB
- references/curated/cross-platform/config-promotion.md 12 KB
- references/curated/cross-platform/core-admin-patterns.md 7.0 KB
- references/curated/cross-platform/foundation-overview.md 7.7 KB
- references/curated/cross-platform/ping-cli-basics.md 6.9 KB
- references/curated/cross-platform/policy-and-branding-basics.md 6.4 KB
- references/curated/cross-platform/tenant-and-environment-setup.md 8.8 KB
- references/curated/ping-software/pingaccess-basics.md 13 KB
- references/curated/ping-software/pingdirectory-basics.md 5.8 KB
- references/curated/ping-software/pingfederate-basics.md 6.6 KB
- references/curated/pingone-mt/admin-roles-and-access.md 11 KB
- references/curated/pingone-mt/app-registration.md 11 KB
- references/curated/pingone-mt/directory-and-populations.md 18 KB
- references/curated/pingone-mt/sign-on-policies.md 14 KB
- references/curated/pingone-mt/tenant-and-environment-setup.md 9.9 KB
- references/curated/pingone-mt/themes-and-branding.md 12 KB
- references/curated/pingone-st/am-services.md 20 KB
- references/curated/pingone-st/app-setup.md 7.1 KB
- references/curated/pingone-st/authentication-fundamentals.md 10 KB
- references/curated/pingone-st/directory-setup.md 7.7 KB
- references/curated/pingone-st/foundation-overview.md 7.4 KB
- references/curated/pingone-st/themes-and-customization.md 6.5 KB
- references/runtime/mcp-preflight.md 3.8 KB
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 · 121 lines · 109 tokens per session scan A fcd8ca7e373f
ping-foundation is a skill published in the GitHub repository pingidentity/agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,705 once invoked, about $0.0005 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 skills, from other repositories
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode.
agent-performance-analyzer
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer.
agent-neural-network
Agent skill for neural-network - invoke with $agent-neural-network.