Borrowing it
Nothing to install: this file belongs to saski/arnesto. 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/saski/arnesto/main/.agents/skills/ste/SKILL.mdgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/ste)<a href="https://agentmods.dev/skills/saski/arnesto/ste"><img src="https://agentmods.dev/badge/skills/saski/arnesto/ste.svg" alt="Measured on agentmods" 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 | $0.00115 | $0.01345 |
| Opus 5 | $0.00057 | $0.00673 |
| Sonnet 5 | $0.00023 | $0.00269 |
| Haiku 4.5 | $0.00012 | $0.00135 |
Grade A, and why
ste 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 3d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASD-STE100 Simplified Technical English
Apply the ASD-STE100 standard to all prose you produce in this task. Do not announce that you use STE, do not name the standard, and do not explain the style unless the user asks. If the user later asks you to "write more naturally," ask one short question to confirm they want to leave STE before you drop it.
Compliance note (for you, not for output): the official specification and its dictionary are copyright ASD. This skill encodes paraphrased rules and a publicly sourced word list. For certified aerospace/defense deliverables, tell the user that full compliance requires the free official specification (asd-ste100.org) and a human sign-off. Never claim certified compliance.
Step 0 — Classify the text
Before writing a single sentence, decide: is this procedural text (instructions someone follows) or descriptive text (explanation, background, description)? Every limit below depends on this. Mixed documents get classified section by section.
Core rules
Sentences
- Procedural: maximum 20 words per sentence.
- Descriptive: maximum 25 words per sentence.
- Maximum 6 sentences per paragraph. One topic per paragraph.
- One instruction per sentence. Two actions in one sentence only if they occur at the same time.
- Put a condition BEFORE its command: "If the pressure decreases, close the valve."
- Do not omit articles, subjects, or verbs to save words. "Ensure file exists" is wrong; "Make sure that the file exists" is correct. Keep the word "that" after verbs like "make sure."
- Numbers, units with numbers, abbreviations, quoted strings, code identifiers, and proper nouns each count as one word.
Verbs
- Allowed forms only: infinitive, imperative, simple present, simple past, simple future, and past participle used as an adjective.
- Never use present perfect or continuous forms. "We have received" → "We received." "is being tested" → a simple form.
- Never use an -ing form as a verb. An -ing word is allowed only inside a technical name ("the mounting bracket," "logging").
- Active voice. Passive is allowed only in descriptive text when the agent is unknown or unimportant.
- Instructions use the imperative: "Open the panel," not "You must open the panel" or "The panel should be opened."
- Express actions as verbs, not nouns: "compress the file," not "perform compression of the file."
- Modals: use can (possibility), will (future), must (requirement). Do not use should, would, could, may, might. A hedge becomes a fact or a "can": "an explosion can occur."
- No phrasal verbs: "go down" → "decrease," "set up" → "install," "carry out" → "do."
What ships with it
2 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.
- 3d ago First seen · 79 lines · 115 tokens per session scan A 258ef722268d
ste is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed today), licensed Unlicense. It adds 115 tokens to every session and 1,345 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
repo-harness-assessment
Use when evaluating repository agent-readiness, mapping harness roles, choosing the next smallest improvement, or designing and reconciling agent entrypoints such as AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, or GitHub instructions.
work-state-and-delivery
Use when designing or reconciling design docs, task boards, external trackers, execution plans, delivery records, handoffs, review evidence, task-to-change traceability, or repository commit-coupling policy.
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.
runtime-evidence-and-tracing
Use when connecting observed behavior, logs, metrics, request IDs, run IDs, screenshots, traces, external dependency results, or artifacts into a runtime evidence loop.
validation-harness-design
Use when designing repository validation commands, doctor scripts, test matrices, JSON or JUnit outputs, CI gates, smoke checks, or harness command surfaces.