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 petar-djukic/writing-skills --skill critic-panelgit clone --depth 1 https://github.com/petar-djukic/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/petar-djukic/writing-skills/critic-panel)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/critic-panel"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/critic-panel/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/petar-djukic/writing-skills/critic-panel"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/critic-panel.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 | $0.04038 |
| Opus 5 | $0.00000 | $0.02019 |
| Sonnet 5 | $0.00000 | $0.00808 |
| Haiku 4.5 | $0.00000 | $0.00404 |
Grade A, and why
critic-panel 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 6d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: critic-panel description: >- Read-only critics for a finished draft, run before voice-critic. Two modes: panel — named persona critics read in parallel from fresh contexts and merge into one sheet with cross-critic convergence first; socratic — one critic interrogates the article with genuine questions anchored to sentences, and the author's written answers become the edit plan. Two critic kinds: suggest critics return line-level original/replacement edits, verdict critics quote the passage and state the finding without rewriting it. Named rosters: article (Levine, Didion, Hemingway) for essays, book (Fowler, Yegge, Deitel, Miller, Cook, Kreischer) for chapter drafts, or any ad-hoc mix. The skill never applies anything; the author picks, and the picks become an author-directed cycle. Triggers: critic panel, read it like Levine, pace critic, turn of phrase, it's only fine, socratic read, interrogate the draft, what would make this better, review chapter, critique my chapter, six critics, is this chapter any good, clarity test, bullshit test, pedagogy test, does this chapter work. argument-hint: 'Path to the draft, plus optionally: --roster article | book | '
Critic Panel (caller's review phase, before voice-critic)
A draft that has cleared every gate is clean, correct, and often only fine — every pass was allowed to remove risk, none was hired to add. This skill hires the adders, on a leash: critics read and propose, the author chooses, and nothing reaches the text except through an author-directed cycle. Its home is the caller's review phase (GH-208), not the humanize chain: a workflow command runs it after the chain's terminal stage (GH-57: after the terminal stage, models read but never write), ahead of voice-critic, because its picks change what voice-critic would audit. Rule-based application of the merged sheet is critic-apply's job.
terminal stage (inject-vernacular)
-> critic-panel (this) read-only: diagnosis + suggestions
-> class sweep read-only: every instance of a named class
-> author picks -> new author-directed cycle (the only way text changes)
-> voice-critic read-only: stance, snark, ToM audit
-> author gate
What ships with it
10 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.
- references/personas.md 13 KB
- scripts/converge.py 18 KB runs code
- scripts/prepare_copy.py 4.1 KB runs code
- scripts/test_critic_panel.py 29 KB runs code
- scripts/testdata/classes-didion.md 953 B
- scripts/testdata/classes-hemingway.md 700 B
- scripts/testdata/didion.md 3.9 KB
- scripts/testdata/hemingway.md 3.2 KB
- scripts/testdata/levine.md 3.9 KB
- scripts/testdata/panel2-golden-sheet.md 11 KB
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.
- 6d ago Changed · +4 lines cccc06f7507d
- 11d ago First seen · 330 lines · 0 tokens per session scan A 73ff8512f216
critic-panel is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,038 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
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
structural-humanizer
Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…
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.