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 skills add pingidentity/agent-plugins --skill ping-skill-writinggit clone --depth 1 https://github.com/pingidentity/agent-pluginsWrote 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/skills/pingidentity/agent-plugins/ping-skill-writing)<a href="https://agentmods.dev/skills/pingidentity/agent-plugins/ping-skill-writing"><img src="https://agentmods.dev/badge/skills/pingidentity/agent-plugins/ping-skill-writing/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.
<a href="https://agentmods.dev/skills/pingidentity/agent-plugins/ping-skill-writing"><img src="https://agentmods.dev/badge/skills/pingidentity/agent-plugins/ping-skill-writing.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00041 | $0.01084 |
| Opus 5 | $0.00020 | $0.00542 |
| Sonnet 5 | $0.00008 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
ping-skill-writing 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ping Skill Writing
Structure, formatting, and content guidance for distributable plugin skills. Use alongside any general-purpose skill-authoring skill.
Structure
Start from assets/templates/SKILL.template.md. Default to one skill per domain, not one per product or activity — keep the number of skills low. SKILL.md is a router: routing tables progressively disclose product- and activity-specific detail from references/ files, so each skill's coverage grows through its references rather than by adding skills.
references/ is a plain tree of maintained content — every file in it is shipped and kept current. There is no "curated" or staging tier.
After any change, run python3 scripts/validate_skills.py --root . — it enforces the skill frontmatter schema (description 50–500 chars), name: matching the directory, SKILL.md ≤ 160 lines, and resolution of inline references/... routing links.
Rules
Keep the description: between 50 and 500 characters
The description is the trigger surface every agent routes on, at a standing context cost in every session. Keep 50–500 chars, packing the highest-value routing tokens (product names, protocols, error strings) and cutting anything an agent could infer from the task itself.
Never cross-link skills as handoffs
Take an "agent knows best" approach: the agent sources its own context and tools from the original prompt. No skill may reference or signpost another inside its content — SKILL.md or references. Inter-skill links create dependencies that break easily and can pull the agent into context the prompt never asked for. The frontmatter description: is the routing surface, not in-content links: phrase it so a prompt like "create an application for PingOne" routes here without the skill ever being named.
- Bad: "Step 1: integrate the XYZ application. To integrate applications, hand off to the
ping-application-integrationskill." - Good: "Step 1: integrate the XYZ application."
Name the concrete task only — the agent knows it needs application integration and will find the best available skill, docs, or tool for it (possibly better than any skill we could point to).
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.
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 · 63 lines · 41 tokens per session scan A e4fc48cfcfb3
ping-skill-writing is a skill published in the GitHub repository pingidentity/agent-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,084 once invoked, about $0.0002 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 2026-09-19.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
session-summaries
What the chat right-panel session summary shows, what it costs, and how to make a session summarize well. Load when the user asks about the session summary panel, why a summary looks wrong or empty, or how to turn it on.
debug
Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning errors, or behaving unexpectedly. Forces structured root-cause analysis before any code change is proposed.
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.