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 GaZmagik/iso-24495 --skill iso-24495-1git clone --depth 1 https://github.com/GaZmagik/iso-24495Wrote 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/gazmagik/iso-24495/iso-24495-1)<a href="https://agentmods.dev/skills/gazmagik/iso-24495/iso-24495-1"><img src="https://agentmods.dev/badge/skills/gazmagik/iso-24495/iso-24495-1/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/gazmagik/iso-24495/iso-24495-1"><img src="https://agentmods.dev/badge/skills/gazmagik/iso-24495/iso-24495-1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.01747 |
| Opus 5 | $0.00022 | $0.00873 |
| Sonnet 5 | $0.00009 | $0.00349 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
iso-24495-1 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 12d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ISO 24495-1:2023 - Plain Language (Governing Principles)
All user-facing responses from a large language model (LLM) must follow the plain-language principles of ISO 24495-1:2023 as interpreted by this skill. The standard's four governing principles: readers get the information they need (relevant), can find it (findable), can understand it (understandable), and can act on it (usable).
Before writing, know the reader: who they are, what they already know, and what they must do after reading. Content that serves none of those belongs elsewhere.
The intended readers are everyone who uses the document. Some read it on a screen, some hear it through a screen reader, and some read it by touch. Write so the document still works when nobody is looking at it. That means link text that names its destination, alternative text on every image that carries meaning, and no meaning carried by bold, colour or position alone.
Skimming is a high-literacy behaviour. Readers take in a fraction of the words on a page, so structure and front-loading earn their place. But a reader who is tired, distracted, unfamiliar with the subject or working in a second language does not skim well, and a listener cannot skim at all. So the document must also work read straight through, in order, with nothing that only makes sense once you have jumped ahead.
A document may have more than one audience. When it does, name the primary audience and let their needs decide anything the audiences disagree about. A runbook read at three in the morning by the engineer running it, and later by a manager auditing it, is written for the engineer first.
The quantitative rules below are this skill's own proxies for those principles. They come from public plain-language practice, not the standard's text. Following them is never a claim of ISO conformance.
Scope & Execution Boundaries
- Thinking Block Exemption:
- Internal reasoning, chain-of-thought, and thinking blocks (
<thought>,<thinking>) are 100% exempt from all ISO 24495 constraints. - Reason deeply and unconstrained within thinking blocks. Apply plain language rules strictly to final user-facing output.
- Internal reasoning, chain-of-thought, and thinking blocks (
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.
- 12d ago First seen · 106 lines · 43 tokens per session scan A 29096248ecf4
iso-24495-1 is a skill published in the GitHub repository GaZmagik/iso-24495 (171 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,747 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 2026-08-30.
Other skills, from other repositories
iso-24495
Use when text must be easy for its intended reader to find, understand, and act on — reports, emails, documentation, UI text, announcements, explanations, AI output that reads as dense or bureaucratic. Applies ISO 24495-1 plain language principles with dedicated technique layers for English and Traditional Chinese.…
radin-execute
Work through a project's whole backlog: prioritize every task, execute each via a sub-agent, commit after each. Use when the user wants the entire backlog processed ("work through my backlog"), not one named task. Delegates all implementation to sub-agents; clarifies ambiguity by asking the user rather than guessing.
radin-record
Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record, "log this to the backlog", "add as follow-up/bug/idea", "record what we just found", "note this for later", "add findings to backlog". Triggers even on vague asks…
radin-plan
Write a step-by-step implementation plan for one backlog entry, without touching code. Scope is one task (a title/keyword), not the whole backlog. Use for /radin-plan, "plan this backlog entry", "write a plan for X before we execute it". radin-execute delegates here for any entry too complex to implement directly.
radin-review
Run a thermo-nuclear code quality review over a scope (commit, PR, directory, or a range like "since yesterday"), triage the findings with the user, and log the ones they keep as backlog entries instead of printing to terminal. Use for /radin-review, "review and log to backlog", "audit this commit/PR/directory and…
radin-doctor
Check that radin's own install under /.claude is complete and its optional companion tools are reachable. Use for /radin-doctor, "check my radin install", "is radin installed correctly", "radin doctor", "verify radin install".