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 nikdumroese/plain-language-skill --skill plain-language-iso-24495git clone --depth 1 https://github.com/nikdumroese/plain-language-skillWrote 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/nikdumroese/plain-language-skill/plain-language-iso-24495)<a href="https://agentmods.dev/skills/nikdumroese/plain-language-skill/plain-language-iso-24495"><img src="https://agentmods.dev/badge/skills/nikdumroese/plain-language-skill/plain-language-iso-24495/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/nikdumroese/plain-language-skill/plain-language-iso-24495"><img src="https://agentmods.dev/badge/skills/nikdumroese/plain-language-skill/plain-language-iso-24495.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 | $0.00152 | $0.01720 |
| Opus 5 | $0.00076 | $0.00860 |
| Sonnet 5 | $0.00030 | $0.00344 |
| Haiku 4.5 | $0.00015 | $0.00172 |
Grade A, and why
plain-language-iso-24495 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plain language (ISO 24495-1:2023)
Apply the four principles to every document: Relevant, Findable, Understandable, Usable. Readers must be able to find what they need, understand it, and use it.
The workflow below is a loop, not a checklist. If new reader information appears at step 3, return to step 1.
References
Load on demand:
references/principles.md— full principles and guidelines.references/checklist.md— 42-item pre-flight review.references/reader-test.md— reader evaluation. External docs only; skip for internal memos.assets/template.md— starting shape for the output. Use it as the default structure.
Step 1 — Identify readers and format (Principle 1)
Before drafting, know:
- Readers: roles or teams. If several, name the primary audience.
- Purpose: what they must do after reading (decide, approve, act, learn).
- Prior knowledge: what they know; adjust vocabulary.
- Reading context: phone, desktop, meeting, Slack link.
- Time available.
- Language: confirm before drafting in English if the reader group is not native.
- Format: a video, form, FAQ, or dashboard may serve better than prose.
Ethics: accurate content, no misleading claims, no hidden content the reader needs.
If any of the above is missing, ask one focused question before drafting. Do not skip.
Step 2 — Structure for findability (Principle 2)
- The most important message goes at the top. The reader knows the ask, decision, or answer within the first screen.
- Multiple audiences get their own labelled section.
- Warnings before instructions.
- Processes in chronological order.
- Headings describe what follows. Scanning headings alone reconstructs the argument.
- Supplementary detail at the end, in a labelled section.
- Apply prominence (bold, callouts), proximity (group related items), similarity (same shape for same function). Use white space to separate ideas.
Step 3 — Write for understandability (Principle 3)
What ships with it
4 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.
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.
- 10d ago First seen · 140 lines · 152 tokens per session scan A 771ea11fbb01
plain-language-iso-24495 is a skill published in the GitHub repository nikdumroese/plain-language-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 1,720 once invoked, about $0.0008 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
fetch-url
Fetch a single URL and convert its content to Markdown. Use when you need to read a web page, documentation page, or API reference without indexing it. The content is returned as plain Markdown text on stdout.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
accessibility
Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…