What is match-structure?

A measurement toolkit for comparing sentence and paragraph patterns across a research-paper collection, including passive voice, hedging, citations, and word usage.

Use it to build a profile of a research corpus, compare documents or sections, track recurring terms and phrases, and check rewritten text for excessive similarity.

It turns writing-style judgments into measurable comparisons and provides similarity checks for other rewriting workflows.

match-structure — Skill for Claude Code and Codex by petar-djukic

Install

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.

Any agent

npx skills add petar-djukic/writing-skills --skill match-structure

Clone the repo

git clone --depth 1 https://github.com/petar-djukic/writing-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/petar-djukic/writing-skills/match-structure/github.svg)](https://agentmods.dev/skills/petar-djukic/writing-skills/match-structure)

Your own site

<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/match-structure"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/match-structure/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/match-structure"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/match-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,838 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00146	$0.01838
Opus 5	$0.00073	$0.00919
Sonnet 5	$0.00029	$0.00368
Haiku 4.5	$0.00015	$0.00184

Measured 11d ago against content hash 257a47899dde, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

match-structure 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 11d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/match_structure.py, scripts/style.py, scripts/testdata/test_diction_weight.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/match-structure/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Split from the original match-structure (GH-291, 2026-07): the section-level driver (compare, blueprint extraction, section-by-section rewrite) moved to match-outline. This skill retains the quantitative metrics engine, corpus aggregation, frequency analysis, and the similarity guard that other prose skills import.

Match structure (paragraph/sentence-level metrics)

This skill provides the quantitative style measurement layer that other prose skills depend on. It profiles markdown papers at the sentence and paragraph level — distributions, passive voice, hedging, citation density, word and phrase frequencies, stock idiom usage — and aggregates those into a corpus profile. It also provides the similarity plagiarism guard used by match-outline's rewrite mode and match-voice's verify step.

Where things live

Corpus: <db-dir>/papers/*.md — the markdown conversions fetched by update-references, selected via entries in references.yaml. Default selection is entries with status: summarized; pass --all to style.py corpus to include every entry with an md_path.
Quantitative profile: <db-dir>/voice-profile.json, written by style.py corpus. Regenerate only when the corpus changes.
Voice anchors: passage-level tf-idf retrieval from writing-voice/ exemplars, via voice_anchors.py.
Venue profiles: writing-voice/venues/<name>.yaml — per-venue parameter bundles (anchor query, blueprint, targets, tell lexicon, gates) consumed by humanize/filter-tells/tighten-style. Schema in the writing-voice repository rule; loader/validator is venue_profile.py.

Running the scripts

RUN="pixi run --manifest-path <skill>/../../pixi.toml python"

style.py subcommands

$RUN <skill>/scripts/style.py --db <db-path> profile <paper.md>   # one paper, full JSON
$RUN <skill>/scripts/style.py --db <db-path> corpus                # aggregate, write voice-profile.json
$RUN <skill>/scripts/style.py --db <db-path> compare <draft.md>    # metric deltas vs corpus
$RUN <skill>/scripts/style.py freq <paper.md>                      # frequency tables only
$RUN <skill>/scripts/style.py similarity <file> --against <sources> [--baseline <draft>]
$RUN <skill>/scripts/style.py burstiness <draft.md> [--baseline <before.md>] [--per-paragraph] [--text]

Read the full file on GitHub · 149 lines

Files

What ships with it

11 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.

Changes

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.

11d ago First seen · 149 lines · 146 tokens per session scan A 257a47899dde

Subscribe to this mod's changes

match-structure is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 7d ago), licensed MIT. It adds 146 tokens to every session and 1,838 once invoked, about $0.0007 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.

Analytics and metrics Claude Code Research ai-detection ai-writing citation-audit claude-skills humanize-ai-text

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…

NulightJens/humanizer-stack · 111 tokens

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.…

NulightJens/humanizer-stack · 188 tokens

match-structure