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 agentmods add skills/paultyng/skill-issue/simplify-prosenpx skills add paultyng/skill-issue --skill simplify-prosegit clone --depth 1 https://github.com/paultyng/skill-issueWrote 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/paultyng/skill-issue/simplify-prose)<a href="https://agentmods.dev/skills/paultyng/skill-issue/simplify-prose"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/simplify-prose.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 | $0.00151 | $0.01985 |
| Opus 5 | $0.00076 | $0.00992 |
| Sonnet 5 | $0.00030 | $0.00397 |
| Haiku 4.5 | $0.00015 | $0.00198 |
Grade A, and why
simplify-prose 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 4d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simplify Prose
Rewrite or check reader-facing technical text with the mechanical core of ASD-STE100 Simplified Technical English (STE), the controlled language aerospace and defense manufacturers use for maintenance manuals. The rules exist so a tired reader who is not a native English speaker cannot misread an instruction. They remove the usual signs of AI slop as a side effect: long sentences, synonym rotation, hedges, filler, decorative clauses.
Write for that tired reader. Each sentence must survive one read.
Scope: where this skill applies
Scope-split with the terse-output rule:
- This skill owns reader-facing technical text (docs, READMEs, runbooks, error messages, release notes, incident reports, agent/system prompts). Keep complete grammar — articles, "that", no telegraph style, no contractions — for non-native readers.
terse-outputowns chat replies, PR/review comments, commit messages, where aggressive word-dropping is right.match-voiceowns marketing, brand, and personal-voice writing. Do not apply this skill there; STE deletes persuasion by design (see Limit).
The modal ladder, slop substitutions, and condition-before-command are shared with terse-output. The completeness rules (keep articles, keep "that", no contractions) are this skill's alone.
Workflow
- Classify each passage as procedural or descriptive. Every other rule depends on this.
- Fix vocabulary before drafting. Pick ONE verb for the check/verify/confirm concept and ONE noun for the config/settings concept. Use no other word for these concepts in the whole document.
- Apply the core rules (below).
- Leave untouchables exact — code, identifiers, commands, quoted errors.
- Run the self-check before delivering. Not optional.
When asked to CHECK text instead of writing it, report each violation as: the offending text, the problem, a compliant rewrite. Use references/checklist.md for the searchable pass.
Classify first
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.
- 4d ago First seen · 114 lines · 151 tokens per session scan A 3cb23250b5f2
simplify-prose is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 23d ago), licensed MIT. It adds 151 tokens to every session and 1,985 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
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
expert
Base expert skill.
alpha
Alpha skill.
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.
codeql
CodeQL operational workflow — discover/config, run/inspect, triage SARIF findings (rule/query ID, source→sink, evidence), remediate, re-validate. Distinguishes broad MegaLinter linting from semantic security analysis.