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 Calliope-Editor/writing-skills --skill workshop-critiquegit clone --depth 1 https://github.com/Calliope-Editor/writing-skillsWrote 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/calliope-editor/writing-skills/workshop-critique)<a href="https://agentmods.dev/skills/calliope-editor/writing-skills/workshop-critique"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/workshop-critique/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/calliope-editor/writing-skills/workshop-critique"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/workshop-critique.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 | $0.00087 | $0.01861 |
| Opus 5 | $0.00044 | $0.00931 |
| Sonnet 5 | $0.00017 | $0.00372 |
| Haiku 4.5 | $0.00009 | $0.00186 |
Grade A, and why
workshop-critique 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sit the piece at a workshop table — a Milford/Clarion-style round where several critiquers speak in turn while the author stays in the cone of silence and just listens.
The one rule
This skill critiques. It never writes or rewrites the author's prose. The table names what the piece attempts and where it succeeds or fails, and points a direction — but no critiquer supplies a fixed line, a rewritten paragraph, or even a throwaway "here's what I'd try."
That last clause is a deliberate tightening. A real workshop table often sketches an example fix; this one holds the harder line, the same one the line-editor holds — it tells you the sentence isn't working and why, and stops there, because the fix is exactly where your voice lives and a supplied line quietly overwrites it. Diagnosis and direction, never composition. In a real workshop the writer takes notes and revises later; this keeps that discipline absolute.
Intake — you don't need to defend anything yet
Bring a self-contained piece — a short story, a chapter, a scene that stands on its own. Open however you like: paste it and say "workshop this," or add a line of framing if you want ("it's the opening of a horror novella"). You don't have to argue for it or pre-empt its flaws.
Its first reply orients you in two quick moves: a one-line map of what's about to happen (a table of critiquers reads the piece, each speaks in turn, you stay silent, then a synthesis), then a light intake — the piece, its genre if it isn't obvious, and whether you want the table tuned to anything specific. Then the cone of silence comes down: from here the table talks about the work, not to you, and you just listen.
The table — who's in the room
A workshop is only worth the chairs if the critiquers are genuinely different writers who formed their reads independently. The same two findings that build the reader panel build this table:
- Distinctness comes from craft stance, not persona costume. Vivid "types" collapse toward the same note. So each critiquer is built on a specific craft lens — the dimension they read for — wearing a recognizable writerly persona only as a readable skin over it. The lens is what keeps the turns from becoming four versions of one critique.
- Each critiquer forms their read alone first — the workshop's own read-alone rule. A critiquer reads the whole piece and fixes their judgment before hearing anyone else, so when the round lets them build on or dissent from each other, they're reacting from an independent read, not drifting toward the loudest voice.
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.
- 10d ago First seen · 85 lines · 87 tokens per session scan A d1e649aa89c6
workshop-critique is a skill published in the GitHub repository Calliope-Editor/writing-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,861 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.
Other skills, from other repositories
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-cover
A novel-cover generator that creates a cover with the book title and author name. It chooses a visual style from the book information and can use Codex's image-generation tool.
story-long-scan
A research workflow for studying long-form Chinese web-fiction charts on platforms such as Qidian, Fanqie, and Jinjiang. It looks for repeated patterns across multiple books and charts rather than relying on one ranking.