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 momentmaker/kaijutsu --skill editorial-reviewgit clone --depth 1 https://github.com/momentmaker/kaijutsuWrote 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/momentmaker/kaijutsu/editorial-review)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/editorial-review"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/editorial-review/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/momentmaker/kaijutsu/editorial-review"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/editorial-review.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 | $0.00097 | $0.03569 |
| Opus 5 | $0.00048 | $0.01784 |
| Sonnet 5 | $0.00019 | $0.00714 |
| Haiku 4.5 | $0.00010 | $0.00357 |
Grade A, and why
editorial-review 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editorial Review
Multi-pass editorial review for long-form essays and articles. Runs after drafting is complete, before publish.
Input
The user provides a file path to the essay. If not provided, look for the most recently modified .md file in the working directory or in content/, essays/, posts/, or drafts/.
The user can also pass a voice config to tune thresholds — see Voice configs below. Default: literary-intelligent-general.
Step 0: Load Context
- Read the essay file completely
- Read any
CLAUDE.md/AGENTS.mdfor project-specific editorial guidelines (if present) - Note the word count
- Note the active voice config (default
literary-intelligent-generalunless user specified otherwise)
Step 1: Structural Pass
Review the essay's architecture:
- Arc: Does the essay move through distinct registers? Is there a turn or complication?
- Transitions: Read the last paragraph of each section and the first paragraph of the next. Does the reader feel carried forward or dropped and reset?
- Pacing: Are there stretches of 2,000+ words at the same analytical register without relief? Flag them.
- Sections: Does each section earn its length? Could any be cut or merged without loss?
- Opening: Does it drop the reader into something specific and sensory within the first paragraph?
- Closing: Does it open rather than close? Does it echo or transform the opening?
Report findings as:
## Structural Pass
- [STRONG] description
- [FIX] description — suggested change
Fix all [FIX] items before proceeding.
Step 2: Line-Level Pass
Read every paragraph checking for:
- Paragraph density: Any paragraph over 6 lines on a mobile screen (roughly 4 sentences of medium length)? Split it.
- Jargon: Any technical or academic term that isn't earned and explained gracefully? Replace with plain English.
- Repetition: Same word, phrase, or construction used in two different sections unintentionally? Vary one instance.
- Rhythm: Three or more consecutive paragraphs opening with the same sentence pattern? Vary.
- Wellness-speak: Any use of "healing," "journey," "transform," "authentic self" that isn't precise and necessary? Cut or replace.
- Inspirational generalities: Any sentence that could appear on a bumper sticker without the surrounding context? Earn it or cut it.
- Telling vs. showing: Any sentence that summarizes an experience instead of rendering it? ("It was profound" → show the specific moment.)
- Proselytizing: Any sentence that tells the reader what to conclude? Rewrite to walk them to the edge and let them look.
- Dead phrases: "One might argue," "it could be said," "in a sense" — cut.
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.
- 10d ago First seen · 276 lines · 97 tokens per session scan A c9cdb284d58d
editorial-review is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 3,569 once invoked, about $0.0005 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
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".