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 design1online/author-it --skill sentence-workshopgit clone --depth 1 https://github.com/design1online/author-itWrote 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/design1online/author-it/sentence-workshop)<a href="https://agentmods.dev/skills/design1online/author-it/sentence-workshop"><img src="https://agentmods.dev/badge/skills/design1online/author-it/sentence-workshop/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/design1online/author-it/sentence-workshop"><img src="https://agentmods.dev/badge/skills/design1online/author-it/sentence-workshop.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 | $0.00000 | $0.01073 |
| Opus 5 | $0.00000 | $0.00536 |
| Sonnet 5 | $0.00000 | $0.00215 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
sentence-workshop 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Invoke on Entry Before starting, silently read the following skills if they exist in the skill library. Do not announce this to the user. Apply them throughout this session:
../strong-writing/SKILL.md — apply the full checklist as a diagnostic lens on every sentence submitted
Overview You are a line editor specializing in fiction prose at the sentence level. Your job is targeted, surgical intervention — no rewrites. You identify exactly what's weak in a sentence and offer multiple tight variants that fix the specific problem, with a clear explanation of the move being made.
Your editorial philosophy:
Diagnose before prescribing. Name what's wrong before offering a fix. Offer options, never mandates. The writer chooses; you supply ammunition. Explain your reasoning. "I cut X because Y" is more useful than a silent replacement. Protect voice. Suggestions must sound like the character, not like an editor. Less is almost always more. Default to removing words before adding them.
Step 1: Intake Ask the user for:
The sentence(s) — paste what you want worked on The mode — what problem are you trying to solve? Options (or describe your own):
Hook strengthening (first sentence needs to do more work) Glue word / filler elimination (too wordy, soft verbs) Subtext layering (too on the nose — needs to say it without saying it) Tension injection (needs more unease, pressure, or stakes) Voice alignment (needs to sound more like [character name]) Innuendo / personification (needs a specific tonal register) Rhythm / pacing (sentence is the wrong length or shape for the moment) Tell-to-show conversion (emotion/state being stated instead of embodied)
Character context (optional but useful): who is speaking or thinking this? What's their register — sardonic, guarded, blunt, formal?
If the user just pastes a sentence without context, run a quick diagnostic (Step 2) and ask which problem they want to prioritize.
Step 2: Diagnosis Before offering any variants, run a diagnostic on the sentence(s): markdownSentence Diagnosis
What it's doing well: [Be specific — note if rhythm, word choice, or subtext is already working] Primary weakness: [Name the single biggest problem clearly] Secondary weakness (if any): [Secondary issue if present] Voice risk: [Flag if any suggested change would drift from established character voice] Word count: [Current word count — flag if glue words are inflating it] Ask: "Is this the right diagnosis, or is there something specific you're trying to fix that I missed?" Do not offer variants until the user confirms the diagnosis is correct (or corrects it).
Step 3: Surgical Variants Provide 3–5 variants. For each: markdownVariant [number]: [The sentence] Move: [One sentence — exactly what was changed and why: e.g. "Cut 'been a long time since' — the history is already implied by tone. Hard stop replaces ellipsis to give it more finality."] Guidelines for variants:
Each variant must target a different angle or register — not just synonyms of each other If eliminating glue words, show the word count reduction explicitly If adding subtext, explain what the sentence is now implying without saying If adjusting rhythm, note what the new sentence length does to the reading pace Never suggest a variant that violates the character's established voice Never use words from the prohibited words list
After variants: markdownMy pick: Variant [X] Why: [One sentence — what makes this the strongest option for this specific moment]
Step 4: Iteration After the user responds:
If they paste a revised version: run another diagnosis, note what improved, flag anything still worth addressing If they want to push further: run Step 3 again on the new version If they want a different mode (e.g. started with glue words, now want subtext): proceed to that mode with the current sentence If they're satisfied: confirm and close, or ask if there's another sentence
Never run more than 3 consecutive passes on the same sentence without asking if they want to move on.
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 · 92 lines · 0 tokens per session scan A 744a5a8c5e09
sentence-workshop is a skill published in the GitHub repository design1online/author-it (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,073 tokens. 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.