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 jtsang4/efficient-coding --skill readwise-researchgit clone --depth 1 https://github.com/jtsang4/efficient-codingWrote 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/jtsang4/efficient-coding/readwise-research)<a href="https://agentmods.dev/skills/jtsang4/efficient-coding/readwise-research"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/readwise-research/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/jtsang4/efficient-coding/readwise-research"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/readwise-research.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 | $0.00160 | $0.02529 |
| Opus 5.5 | $0.00064 | $0.01012 |
| Sonnet 5.5 | $0.00032 | $0.00506 |
| Haiku 4.5 | $0.00016 | $0.00253 |
Grade A, and why
readwise-research 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 1mo 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
readwise-research
Turn the user's Readwise library into a research desk. Find the most relevant documents and highlights for a topic, synthesize them into a structured memo, and only then propose any cleanup or organization actions.
Preflight
- Use the local
readwiseCLI for all retrieval and write operations in this skill. - Use
--jsonfor any command whose output you will inspect programmatically. - If the CLI is missing, install it with
npm install -g @readwise/cli. - If the CLI is present but unauthenticated, ask the user for a Readwise access token from
https://readwise.io/access_token, then runreadwise login-with-token <token>.
Core Defaults
- Treat this as a research task first and an organizing task second.
- Default to read-only analysis. Never mutate Reader unless the user explicitly confirms the proposed actions.
- If the user is asking about what they have read, saved, highlighted, or been reading lately, assume the source of truth is their Readwise library and start there.
- Do not start with web search or generic outside knowledge when the task is about the user's own reading history.
- Use documents as the primary units of analysis and highlights as evidence.
- If the user gives a theme but not a precise question, turn it into a working research question and say that you did so.
- If the request is too broad, narrow the scope and explain how you narrowed it.
- If the user does not specify locations, search across
new,later,shortlist, andarchive. Includefeedonly if they explicitly ask for it. - Prefer 3-6 deeply inspected documents over a long dump of shallow hits.
Interpret the Request
Before searching, extract or infer:
topic: the central theme, question, or projectscope: what angle matters most, such as arguments, tactics, disagreements, definitions, or exampleslocations: optional Reader locations to includetime_window: optional recency constrainttags: optional tag filteraction_mode: whether the user wants analysis only, suggestions, or confirmed mutations
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.
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.
- 1mo ago First seen · 253 lines · 160 tokens per session scan A 826d2aa9afbe
readwise-research is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 8d ago), licensed MIT. It adds 160 tokens to every session and 2,529 once invoked, about $0.0006 per session on Opus 5.5. 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
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.