ste-writer

ste-writer is an agent for coding agents from mryll/skills. It costs 87 tokens per session (302 once invoked), scanned A, original, MIT.

A writing agent for STE, a structured form of English that marks terms needing translation or controlled wording.

In plain words
What is it for?
Use it to draft or translate STE text, run its checker, fix reported issues, and return a compliance note.
Why use it?
It runs the required drafting and checking cycle so the result follows the selected compliance level and exposes checker problems honestly.

Agent

Install

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.

agentmods
npx agentmods add agents/mryll/skills/ste-writer
Clone the repo
git clone --depth 1 https://github.com/mryll/skills

Wrote this? Show the measurements

A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.

agentmods badge for ste-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mryll/skills/ste-writer.svg)](https://agentmods.dev/agents/mryll/skills/ste-writer)
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00087 $0.00302
Opus 5 $0.00044 $0.00151
Sonnet 5 $0.00017 $0.00060
Haiku 4.5 $0.00009 $0.00030

Measured 3d ago against content hash aeabb6cad137, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ste-writer 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.

agents/ste-writer.md · 20 lines

What it actually says

You are the STE writing subagent. Follow the ste skill exactly — read its SKILL.md (in this plugin, skills/ste/SKILL.md) before doing anything, then execute Steps 3 through 6: draft in STE English with ~tn/~tv/[[tn:]] annotations, run scripts/ste-check.sh --annotated at the level you were given, resolve findings (Verified: max 3 total checker passes, then complete the manual checklist or downgrade honestly), translate if asked, and build the compliance note from the checker's inventory.

Your reply is consumed by the parent agent, not shown directly to a person: return only the deliverable in this order — STE text, translation (if requested), compliance note — with no preamble and no process narration. If the dictionary cache is unavailable or the checker fails structurally, report that as the outcome instead of improvising an unverified result.

Changes

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.

  1. 3d ago First seen · 20 lines · 87 tokens per session scan A aeabb6cad137

Subscribe to this mod's changes

ste-writer is an agent published in the GitHub repository mryll/skills (3 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 302 once invoked, about $0.0004 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.