rhetorical-devices

rhetorical-devices is a skill for Claude Code, Codex from Wondermonger-daydreaming/claude-skills-library. It costs 226 tokens per session (1,509 once invoked), scanned A, original, MIT.

A practical guide to rhetorical devices: deliberate patterns in language such as repeated openings, mirrored structures, missing conjunctions, or wordplay. It supports both using these patterns and recognising them in existing writing.

In plain words
What is it for?
Use it to write or closely analyse speeches, essays, poetry, and other prose.
Why use it?
It helps you choose a form that gives a sentence a particular effect and explain how a passage creates that effect.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to write or closely analyse speeches, essays, poetry, and other prose.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wondermonger-daydreaming/claude-skills-library/rhetorical-devices
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 Wondermonger-daydreaming/claude-skills-library --skill rhetorical-devices
Clone the repo
git clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-library

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.

agentmods badge for rhetorical-devices

README.md
[![agentmods](https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/rhetorical-devices/github.svg)](https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/rhetorical-devices)
Your own site
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/rhetorical-devices"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/rhetorical-devices/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.

agentmods 80×15 button for rhetorical-devices

Your own site · 80×15
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/rhetorical-devices"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/rhetorical-devices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 226 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,509 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00226 $0.01509
Opus 5 $0.00113 $0.00754
Sonnet 5 $0.00045 $0.00302
Haiku 4.5 $0.00023 $0.00151

Measured 9d ago against content hash 51ad2b4726d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

rhetorical-devices 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 9d 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.

skills/rhetorical-devices/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rhetorical Devices

Seed, not scripture

The source hands over a long list of named figures and says: be aware of them in generation and in parsing. The list is a starting toolkit, not a closed canon to recite. The skill isn't memorizing forty Greek terms — it's the working fluency where the right figure arrives because the thought has that shape, and where you can name what another's prose is doing because you feel the shape, not because you matched a glossary. Treat the catalogue below as a tuning of the ear, then forget it and listen.

Two functions

Deploy — reach for the figure that does the job the sentence needs. Detect — name the device when close-reading, so the analysis can say how an effect is made. The same fluency runs both ways.

The toolkit (by what they do)

  • Built repetition (schemes of arrangement). Anaphora (same opening, line after line), epistrophe (same ending), symploce (both at once), anadiplosis (end of one clause begins the next), epanalepsis (begin and end with the same word), epizeuxis (immediate insistent repeat), isocolon (parallel equal-length members), asyndeton (no conjunctions — speed, accumulation), polysyndeton (conjunctions piled — weight, ritual).
  • The turned mirror. Chiasmus (ABBA structure) and its strict word-level form antimetabole (the same words reversed: "ask not what your country…"). The figure of reversal, balance, and the trap that springs on the turn.
  • Word- and sound-play. Polyptoton (same root, different forms), antanaclasis (same word, shifted sense), paronomasia (the pun), antimeria (one part of speech used as another — verbing the noun), alliteration / assonance / consonance (front, vowel, and trailing sound-echo).
  • The yoke. Zeugma / syllepsis — one word governing two others it fits in different senses ("he held his tongue and his ground"). Hendiadys — one idea split into two joined nouns ("sound and fury").
  • The meaning-swerve (tropes). Metonymy (the associated thing — "the crown"), synecdoche (part for whole), metalepsis (a chain of association compressed), catachresis (the deliberately wrong/strained term, a borrowed word for the unnamed), hypallage (the transferred epithet — "the condemned cell"), synesthesia (one sense in another's terms — "loud color"), oxymoron (yoked contradiction), prosopopoeia / apostrophe (giving voice to / addressing the absent or abstract), periphrasis (the elaborate roundabout).
  • Under and over. Litotes (affirm by negating the contrary — "not bad"), meiosis (deliberate understatement), auxesis (mounting amplification), pleonasm (intentional redundancy).
  • Disrupted order and breakage. Hyperbaton / anastrophe (words out of expected order for stress), tmesis (a word split by another — "abso-bloody-lutely"), anacoluthon (a sentence that abandons its own grammar mid-flight), aposiopesis (the deliberate break-off into silence), paraprosdokian (the swerve ending that recasts what came before), enallage (a deliberate grammatical "error" for effect).

Read the full file on GitHub · 45 lines

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.

  1. 9d ago First seen · 45 lines · 226 tokens per session scan A 51ad2b4726d4

Subscribe to this mod's changes

rhetorical-devices is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 226 tokens to every session and 1,509 once invoked, about $0.0011 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 2026-09-03.

Related

Other skills, from other repositories

offensive-vuln-classes

Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…

SnailSploit/Claude-Red · 0 tokens

stuck

Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…

mshadmanrahman/claude-for-designers · 161 tokens

canvas-homework

Check Canvas for outstanding assignments and either surface the assignment, or draft a response in Max's voice. Use whenever Max asks what assignments / homework / coursework he still has to do, asks to pull an assignment's instructions or files from Canvas, or asks to start/draft an assignment. Orchestrates the…

98ping/chip · 92 tokens

myopenmath

Work a MyOpenMath / IMathAS math homework set that is launched from Canvas — read the questions, compute the answers, fill the boxes, and submit. Use whenever Max points at a MyOpenMath assignment, says a math homework is "in my Canvas", asks to do/finish/check a numbered homework like "2.1" or "2.2/2.3", or when a…

98ping/chip · 128 tokens

canvas-quiz

Work a Canvas-native quiz (Classic Quizzes) — find it, open the attempt, read every question, save it to output/, fill the answers, and stop short of submitting. Use whenever Max points at a Canvas quiz, asks about a "syllabus quiz" or a quiz he still has to take, asks what a quiz is asking, or when a Canvas…

98ping/chip · 117 tokens

mylab-pearson

Work a Pearson MyLab / MyLab Statistics / MathXL homework set or quiz — launch it through the popup, read each question, compute, fill the answer boxes, and submit. Use whenever Max points at a MyLab, MyLab Stats, Mastering, MathXL or Pearson assignment, says a stats homework is "in MyLab", asks to do/finish/check a…

98ping/chip · 181 tokens