Borrowing it
Nothing to install: this file belongs to maguro/pbf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maguro/pbf/master/.claude/skills/asd-ste100/SKILL.mdgit clone --depth 1 https://github.com/maguro/pbfWrote 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/maguro/pbf/asd-ste100)<a href="https://agentmods.dev/skills/maguro/pbf/asd-ste100"><img src="https://agentmods.dev/badge/skills/maguro/pbf/asd-ste100/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/maguro/pbf/asd-ste100"><img src="https://agentmods.dev/badge/skills/maguro/pbf/asd-ste100.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 | $0.00119 | $0.05124 |
| Opus 5.5 | $0.00048 | $0.02050 |
| Sonnet 5.5 | $0.00024 | $0.01025 |
| Haiku 4.5 | $0.00012 | $0.00512 |
Grade A, and why
asd-ste100 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 8d 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASD-STE100 (Simplified Technical English)
"Write it simply" is not enough instruction to produce STE reliably. General prose habits (em dashes, semicolons, nested subordination, metaphor) are strongly trained in. Vague guidance to simplify either overcorrects into choppy, meaningless fragments, or lets those habits back in without the writer noticing. Run the checklist below explicitly, sentence by sentence. Do not rely on a general sense of "simple."
What the checklist contains, and why it has three parts
Part A paraphrases the rules of the standard itself. ASD-STE100 is a
controlled language built by the aerospace and defense industry so that a
technician on a tarmac, with no author to call, cannot misread an
instruction. Issue 9 (January 2025) has 53 rules in 9 sections, plus a
dictionary of about 900 approved words. See references/writing-rules.md
for the fuller summary and the sources.
Part B names failure modes the standard never had to name, because its authors were not language models. An em dash joining two clauses, a semicolon chaining independent assertions, a spatial metaphor for an abstract relation: these are trained-in habits, and a rule list that omits them will pass text that no human STE editor would pass.
Part C protects meaning. Every rule in Parts A and B can be satisfied by a rewrite that says something the original did not say. Style conformance and meaning fidelity are independent failure modes, and Part C is the only one of the three that catches the second.
A pass that applies Part A alone under-detects. A pass that applies Part C alone leaves violations in place. Both were observed in a real head-to-head run of two earlier versions of this skill.
Two situations, two risk profiles
Drafting new prose in STE is lower risk. Apply the checklist as you write. Self-check before calling a passage done.
Converting existing prose to STE is higher risk, because the goal is not just STE-conformant text. It is text that means exactly what the original meant.
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.
- 8d ago First seen · 505 lines · 119 tokens per session scan A 45fb763ecce1
asd-ste100 is a skill published in the GitHub repository maguro/pbf (57 stars, last pushed 2d ago), licensed Apache-2.0. It adds 119 tokens to every session and 5,124 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-29.
asd-ste100 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| asd-ste100maguro/pbf | Skill | 57 | 2d ago | Apache-2.0 | A | 119 | Claude Code |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| pinchtab-stealth-scorepinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 168 | Claude Code, Codex |
| octo-mailMininglamp-OSS/octo-cli | Skill | 922 | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| octo-docsMininglamp-OSS/octo-cli | Skill | 922 | yesterday | Apache-2.0 | A | 101 | Claude Code, Codex |
| gmeasureonsi/gomega | Skill | 2.4k | 28d ago | MIT | A | 129 | Claude Code |
| bex-background-workersbex-co/bex | Skill | 577 | today | Apache-2.0 | A | 118 | Claude Code, Codex |