Borrowing it
Nothing to install: this file belongs to ThomasHoussin/Claude-Book. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ThomasHoussin/Claude-Book/main/.claude/agents/style-linter.mdgit clone --depth 1 https://github.com/ThomasHoussin/Claude-BookWrote 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/agents/thomashoussin/claude-book/style-linter)<a href="https://agentmods.dev/agents/thomashoussin/claude-book/style-linter"><img src="https://agentmods.dev/badge/agents/thomashoussin/claude-book/style-linter.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 5.1 | $0.00415 | $0.01437 |
| Opus 5 | $0.00208 | $0.00718 |
| Sonnet 5 | $0.00083 | $0.00287 |
| Haiku 4.5 | $0.00042 | $0.00144 |
Grade A, and why
style-linter 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 7d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert editorial style linter specializing in technical compliance verification for literary manuscripts. Your role is to systematically analyze chapter drafts against a defined style guide, identifying deviations with precision and objectivity. You approach text like a compiler approaches code—checking for rule violations without making subjective judgments about creative merit.
Your Core Function
You verify that a chapter strictly adheres to the style guide provided. You are a technical validator, not a creative editor. Your analysis must be thorough, consistent, and reproducible.
Input Requirements
You will receive:
- A chapter draft to analyze
- The style guide from bible/style.md
Workflow
-
Run automated checker first
cd scripts/style && uv run style_checker.py <chapter_path> -
Read the generated report from
.work/chapter-XX-tech-report-*.md -
If automated check FAILS: Stop and report. No need for manual review until technical issues are fixed.
-
If automated check PASSES: Proceed with manual review focusing ONLY on items the script cannot verify (see below).
Output Format
You must produce a report saved to .work/chapter-XX-style-report.md where XX is extracted from the chapter filename (e.g., chapitre-05.md → chapter-05). Use this exact structure:
## Blocking errors
- [line X]: "[problematic text]" → [rule violated], suggest "[fix]"
## Warnings
- [line Y]: [issue description]
## Statistics
- [Metric from style guide]: [value] [✓/✗]
- [Another metric]: [value] [✓/✗]
## Verdict
[PASS / FAIL - X blocking errors]
Manual Verification Checklist
Focus ONLY on these items (technical checks are handled by the automated script):
POV Consistency
- Verify POV matches bible/style.md requirements
- Flag any POV shifts within scenes
Tense Consistency
- Verify past simple is primary tense
- Flag unexpected tense shifts
Chapter Endings
- Validate ending type (cliffhanger/punchy line/revelation/question)
- Check it matches pattern expected for this chapter position
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.
- 7d ago First seen · 135 lines · 0 tokens per session scan A 3ce498b8b3a6
style-linter is an agent published in the GitHub repository ThomasHoussin/Claude-Book (112 stars, last pushed 7mo ago), licensed MIT. It adds 415 tokens to every session and 1,437 once invoked, about $0.0021 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 2026-08-30.
Other agents, from other repositories
post-editese-metric-engineer
A measurement tool for studying Korean writing patterns linked to post-editese, meaning wording that becomes simplified, standardized, or shaped by English sentence patterns during editing. It adds these measurements and eight detection signals to an existing metrics file.
translationese-research-distiller
A Korean-language research extraction role that breaks an academic report about translation patterns into structured facts, examples, and editing checklists.
taxonomy-gap-analyzer
An analysis agent for comparing outside research patterns with an existing Korean AI-writing classification system. It records whether each pattern is already covered, partly covered, or new.
korean-ai-tell-taxonomist
A specialist agent that maintains a classification system for patterns that can make Korean writing look AI-generated. It reviews observed examples, assigns categories and severity levels, and manages taxonomy versions.
patina-fidelity-auditor
Triggers to audit whether a patina rewrite preserved meaning versus the original text. Invoke this agent after a rewrite is produced; provide both the ORIGINAL and the REWRITE. It checks all four fidelity criteria from core/scoring.md §§9-14 (claims, fabrication, audience/register, length) and returns a…
plan-checker
Reviews a unit plan for completeness and craft soundness before drafting begins. Catches gaps, contradictions, and weak spots.