A skill for working with Readwise Original, a service that stores and reviews book highlights and other saved passages. It uses the service's API, meaning a programmed connection to its data.

It helps review daily highlights, find highlights from books, export them as Markdown, and save new highlights.

It avoids manually finding, exporting, organizing, and reviewing highlights. It also handles pagination, retries, rate limits, and optional preview-only changes.

readwise — Skill by ryanlyn

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.

agentmods

npx agentmods add skills/ryanlyn/readwise-skill/readwise

Any agent

npx skills add ryanlyn/readwise-skill --skill readwise

Clone the repo

git clone --depth 1 https://github.com/ryanlyn/readwise-skill

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,078 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00025	$0.02078
Opus 5	$0.00013	$0.01039
Sonnet 5	$0.00005	$0.00416
Haiku 4.5	$0.00003	$0.00208

Measured 2d ago against content hash 215e3b4d3e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

readwise 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/readwise_client.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.

plugins/readwise/skills/readwise/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Readwise Original Skill

Use this skill to automate work with the Readwise "Original" API that powers highlight exports and metadata management.

Quick start

Generate a token from https://readwise.io/access_token and store it in READWISE_TOKEN.
Use uv run --project ${CLAUDE_PLUGIN_ROOT} python ${CLAUDE_PLUGIN_ROOT}/skills/readwise/scripts/readwise_client.py ... instead of calling the API directly; it handles retries, pagination, rate-limit surfacing, --dry-run, and tagging rules.
Keep requests below the documented rate limit (currently 60 req/min). Batch operations and pause between pages when processing large libraries.

Example workflows

"Summarize my daily review and save highlights to a note" — uses highlights review to fetch today's highlights, then formats them
"Find all highlights from Meditations and export as markdown" — uses books to find the book ID, then highlights list to fetch
"Save this quote to my Readwise" — uses highlight create with the quote text

CLI commands

Global options --dry-run and --raw can appear anywhere in the command.

uv run --project ${CLAUDE_PLUGIN_ROOT} python ${CLAUDE_PLUGIN_ROOT}/skills/readwise/scripts/readwise_client.py [--dry-run] [--raw] highlight create --text ... [--book-id ID] [--title ...] [--author ...] [--category ...] [--image-url ...] [--generated] [--tags t1,t2] Creates a highlight or batch (--bulk-file ndjson). Use --book-id to target an existing book (the CLI resolves it to title/author/category for the API). Always specify --category when creating new sources—see "Category is critical" below. Use --image-url for cover images (recommended for books and podcasts, not needed for articles or tweets). If --generated is set, .generated is appended to tags and location_type defaults to none.
... [--dry-run] highlight update <id> [--title --note --tags --generated] – partial updates.
... highlight show <id> – fetch highlight details.
... highlight delete <id> [--yes] – delete a highlight, --yes skips confirmation.
... highlights list [--book-id 123] [--tag focus] [--category books] [--updated-after 2026-02-01] [--limit 50] – cursor-based listing. Dates are ISO format (e.g. 2026-02-01 or 2026-02-01T10:30:00Z).
... highlights review – fetches today's daily review highlights (no parameters; returns the curated spaced-repetition set).
... books [--title ...] [--author ...] [--limit N] – search books by title/author (case-insensitive substring match).
... book <id> – fetch a single book's metadata.
... auth validate – confirms your token works by hitting the /api/v2/auth/ endpoint.

Read the full file on GitHub · 102 lines

Files

What ships with it

1 file 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.

scripts/readwise_client.py 21 KB runs code

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.

2d ago First seen · 102 lines · 25 tokens per session scan A 215e3b4d3e18

Subscribe to this mod's changes

readwise is a skill published in the GitHub repository ryanlyn/readwise-skill (24 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 2,078 once invoked, about $0.0001 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.

Backend and APIs Code review

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens