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 xonika9/agent-skills --skill x9-explain-againgit clone --depth 1 https://github.com/xonika9/agent-skillsWrote 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/xonika9/agent-skills/x9-explain-again)<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-explain-again"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-explain-again/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/xonika9/agent-skills/x9-explain-again"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-explain-again.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 | $0.00098 | $0.00430 |
| Opus 5 | $0.00049 | $0.00215 |
| Sonnet 5 | $0.00020 | $0.00086 |
| Haiku 4.5 | $0.00010 | $0.00043 |
Grade A, and why
x9-explain-again 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 9d 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.
What it actually says
Explain again
Repair understanding of one fragment of the immediately previous substantive assistant answer. This is a model-invoked skill in Claude Code and Codex; portable means structural compatibility only, not verified invocation behavior.
Trigger boundary
Use this skill only when the user's message is explicit confusion about the immediately preceding substantive answer in the same thread. That answer is an assistant response to the user, excluding tool output, status updates, system messages, and imported older chats.
Do not treat a general request to explain a topic as a reference to a prior answer. Explaining a provided article or source remains a source-explanation task. Creating a durable visual teaching artifact belongs to ce-explain; creating a visual scheme belongs to x9-diagrams.
Response
Identify the specific claim, conclusion, example, or step that is unclear. Add only the context needed to make that fragment understandable, then use a different explanatory method: an analogy, a concrete example, a causal breakdown, or simpler words. Include a tiny example only when it resolves the confusion.
Do not merely shorten or repeat the earlier wording. Do not create files, invoke ce-explain or x9-diagrams automatically, or start an autonomous loop. If the user still does not understand, one more bounded explanation is allowed; each new request still needs a clear referent.
When the unclear referent cannot be determined, ask one short question and do not invent context.
Completion
Return either a concise explanation that addresses the identified fragment through a different method, or one short clarifying question when the fragment is not identifiable.
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.
- 9d ago First seen · 27 lines · 98 tokens per session scan A ce3616d8edd5
x9-explain-again is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 430 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
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
api-security
Authorized security assessment of REST, GraphQL, WebSocket, and SOAP APIs: discovery, authentication and authorization flaws (BOLA/IDOR, JWT/OAuth), rate-limit testing, and a structured multi-phase methodology.
aria
Designs the data model, API contracts, and structural foundation of the system.