Agent skill

Read

by davepoon in davepoon/buildwithclaude

Preview a distilled wiki page from inside Claude Code. An agent skill from davepoon/buildwithclaude.

MITAuto-check: notes

Install Read

skills CLI
$ npx skills add davepoon/buildwithclaude --skill read -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install davepoon/buildwithclaude read --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/origin/skills/read .claude/skills/read && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
read
GitHub stars
3.6k
Token cost
~1.2k tokens
SKILL.md length
536 words
Files
1
Skills in repo
246
Repo updated
First seen
Licence
MIT

At a glance

Preview a distilled wiki page from inside Claude Code. An agent skill from davepoon/buildwithclaude.

  • Works in 2 steps: Direct id → Title or freeform word
  • SKILL.md covers How to invoke, Output shape, When to use and When NOT to use
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Read is an agent skill from davepoon/buildwithclaude. Preview a distilled wiki page from inside Claude Code. Prints title, summary, source count, and the local md path. Full body lives on disk — open with the user's editor. Invoked as /read <titleorid.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw. The licence is MIT.

Example prompts

  • “/read”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): mcp__plugin_origin_origin__get_page, mcp__plugin_origin_origin__search_pages, mcp__plugin_origin_origin__get_page_links, Bash

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Direct id
  2. Title or freeform word

What it can do on your machine

Read from SKILL.md and the folder at commit 10bfc43. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • mcp__plugin_origin_origin__get_page
    • mcp__plugin_origin_origin__search_pages
    • mcp__plugin_origin_origin__get_page_links
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Read loads about 1.2k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 536 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: mcp__plugin_origin_origin__get_page, mcp__plugin_origin_origin__search_pages, mcp__plugin_origin_ori

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davepoon/buildwithclaude at commit 10bfc43, republished under its MIT licence (© davepoon). 536 words, ~1,243 tokens.

Download SKILL.mdSave it as .claude/skills/read/SKILL.md (or your agent's skills folder).
name
read
description
Preview a distilled wiki page from inside Claude Code. Prints title, summary, source count, and the local md path. Full body lives on disk — open with the user's editor. Invoked as `/read <title_or_id>`.
allowed-tools
mcp__plugin_origin_origin__get_page, mcp__plugin_origin_origin__search_pages, mcp__plugin_origin_origin__get_page_links, Bash
argument-hint
<title_or_id>

/read

Surface a page's identity so the user can decide whether to open it. /read is preview, not full text. The body is on disk; preview keeps chat scannable, dodges Bash output truncation, and respects the "md is canonical, viewer is the user's editor" model.

How to invoke

Two shapes accepted:

  1. Page id (starts with page_; legacy concept_ ids still work) → direct fetch.
  2. Title or freeform word → search, pick best match, fetch.

Both end with the same preview block.

1. Direct id

Call the MCP tool to fetch the page:

get_page(page_id="<id>")

The response is a JSON object wrapping { "page": {...} }. Read title, summary, space, and source_memory_ids off the page, then look up the md filename in ~/.origin/pages/.origin/state.json:

Bash: python3 -c '
import json, os, sys
state_path = os.path.expanduser("~/.origin/pages/.origin/state.json")
pid = "<id>"
filename = None
try:
    with open(state_path) as f:
        filename = json.load(f).get("pages", {}).get(pid, {}).get("file")
except FileNotFoundError:
    pass
print(f"~/.origin/pages/{filename}" if filename else "(no md projection on disk)")
'

Combine the page fields with the resolved md path and emit the preview block.

2. Title or freeform word

Search first, then fetch the top hit by id and run the same preview block. Always resolve through the search_pages MCP tool — never derive a slug client-side (skill heuristics drift from the canonical slugify() on apostrophes and punctuation).

search_pages(query="<arg>", limit=1)

Parse the returned JSON — the response shape is { "pages": [...] }. Read the first hit's id. If pages is empty, tell the user "no page found matching <arg> — try /distill <arg> to create one" and stop. Otherwise call get_page(page_id=<id>) and emit the same preview block from section 1.

Output shape

Always print exactly these lines (no body):

Title:    <title>
Version:  v<N> — <last_edited_by> <relative_time> (<last_delta_summary>)
Summary:  <one sentence>
Sources:  <N> memories
Space:    <space or (none)>
Links:    <N inbound, M outbound (<K> broken)>
Open:     ~/.origin/pages/<slug>.md
⚠ Stale: <stale_reason> — run /distill to refresh

Lock banner rule:

When the page payload returned by get_page has user_edited == true, prepend this line as the very first line of the rendered output, before the title:

🔒 You've edited this page. Auto-refresh paused. `/distill rebuild <page-id>` to unlock.

Substitute <page-id> with the actual page.id value. When user_edited is false or absent, omit this line entirely.

The lock means daemon distill cycles will not auto-rewrite this page's prose from sources — edits stay until the user explicitly runs /distill rebuild to wipe and regenerate.

Version line rules:

  • Always show v<N>. When version is null or missing, omit the line.
  • Append — <last_edited_by> when populated (e.g. re_distill, user, agent).
  • Append relative time when last_edited_at is set (e.g. 2h ago, 3d ago).
  • Append (<last_delta_summary>) when the field is non-empty.
  • Examples:
    • v1 — synthesized 4h ago
    • v4 — re_distill 2h ago (+mem_xyz, +250 chars)
    • v3 — user 1d ago
Show full SKILL.md (177 more words)Show less

Stale warning rule:

  • Emit the ⚠ Stale: line only when stale_reason is non-null/non-empty.
  • Render stale_reason verbatim (daemon sets it; values like source_updated, new_memories are human-readable enough).

Links line rules (unchanged): Call get_page_links(page_id="<id>") right after get_page and count:

  • inbound = len(inbound)
  • outbound = len(outbound)
  • broken = outbound entries where target_page_id is null

Omit the parenthetical when broken is zero. Drop the line entirely if inbound + outbound is zero.

Don't paraphrase the title, don't trim the summary, don't decorate the preview. The block is one screen, predictable, easy to skim.

If the user wants the full body, they open the md file in their editor (Obsidian, VS Code, glow, bat, …). The plugin doesn't render markdown better than their tools do.

When to use

  • User asks "show me the page on X", "what's in <title>", "preview that".
  • After /distill finishes, follow up with /read "<title>" (titles survive any rendering surface; ids may visually truncate).

When NOT to use

  • Raw memory lookups → use /recall.
  • Listing all pages → list_pages_recent MCP tool or ls ~/.origin/pages/.
  • Reading the full body → open the md file in the user's editor.

© davepoon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/origin/skills/read of davepoon/buildwithclaude.

Open the folder on GitHubat commit 10bfc43

Compare with similar skills

Read next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Read compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Read this skilldavepoon/buildwithclaude3.6k—~1.2kAutomated safety check: NotesMIT
LLM WikiYeachan-Heo/oh-my-claudecode40k—~721Automated safety check: PassMIT
Wiki Querypaperclipai/paperclip98k—~682Automated safety check: PassMIT
Paperclip Distillpaperclipai/paperclip98k—~2.8kAutomated safety check: PassMIT
Wiki Lintpaperclipai/paperclip98k—~878Automated safety check: PassMIT
Wiki Ingestpaperclipai/paperclip98k—~933Automated safety check: PassMIT

Similar skills

  • LLM Wiki

    Yeachan-Heo/oh-my-claudecode

    Keeps a persistent markdown wiki of project and session knowledge that the agent can ingest into, query, lint and read across sessions.

    40k GitHub stars~721 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Wiki Query

    paperclipai/paperclip

    A skill your agent uses when an LLM Wiki operation issue asks a question.

    98k GitHub stars~682 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Paperclip Distill

    paperclipai/paperclip

    A skill your agent uses when an operation issue is a Paperclip cursor-window, distill, or backfill.

    98k GitHub stars~2.8k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Wiki Lint

    paperclipai/paperclip

    A skill your agent uses when an LLM Wiki operation issue is a lint or health check.

    98k GitHub stars~878 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Wiki Ingest

    paperclipai/paperclip

    A skill your agent uses when an operation issue asks to ingest a captured raw/ source into the LLM Wiki, or the user says "ingest <slug".

    98k GitHub stars~933 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Wiki Builder

    sickn33/agentic-awesome-skills

    Create and maintain reusable research wikis with source provenance, configurable structure, and local markdown outputs.

    47k GitHub starsUsed in 1 repo~1.4k tokens
    Knowledge ManagementAuto-check passed

More from davepoon/buildwithclaude

All 246 skills in this repo
  • Qwen Vision

    davepoon/buildwithclaude

    A skill your agent uses when the user asks to "analyze video", "watch this video", "what happens in this video", "describe this clip", "review this footage", "classify these videos", "compare…

    3.6k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Hard Predict Future

    davepoon/buildwithclaude

    Activate this agent for any future-oriented question that requires deep quantitative analysis, historical precedents, and structured scenario planning.

    3.6k GitHub starsUsed in 1 repo~4.2k tokens
    Auto-check passed
  • iOS Hig Design Guide

    davepoon/buildwithclaude

    Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data.

    3.6k GitHub stars~735 tokensUpdated yesterday
    Auto-check passed
  • Video Downloader

    davepoon/buildwithclaude

    Download YouTube videos with customizable quality and format options.

    3.6k GitHub starsUsed in 1 repo~871 tokens
    Auto-check passed
  • Atlas Cloud Media

    davepoon/buildwithclaude

    Discover Atlas Cloud image and video models, inspect their live schemas, and submit one confirmed media generation request with bounded GET polling.

    3.6k GitHub stars~852 tokensUpdated yesterday
    Auto-check passed
  • Slack Gif Creator

    davepoon/buildwithclaude

    Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives.

    3.6k GitHub starsUsed in 12 repos~4.3k tokens
    Auto-check passed

Questions about Read

What does Read do?

Preview a distilled wiki page from inside Claude Code. An agent skill from davepoon/buildwithclaude. Read is an agent skill from davepoon/buildwithclaude. Preview a distilled wiki page from inside Claude Code.

How do I install Read in Claude Code?

Run `npx skills add davepoon/buildwithclaude --skill read -a claude-code`. Or copy the skill folder (plugins/origin/skills/read in davepoon/buildwithclaude) into .claude/skills/read in your project. Claude Code loads it when a task matches its description.

How do I install Read in Codex?

Run `npx skills add davepoon/buildwithclaude --skill read -a codex`. Or copy the skill folder (plugins/origin/skills/read in davepoon/buildwithclaude) into .agents/skills/read in your project. Codex loads it when a task matches its description.

Can I use Read in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davepoon/buildwithclaude --skill read -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/read, .gemini/skills/read, .github/skills/read and .opencode/skills/read in your project.

What does Read need to run?

SKILL.md names no scripts, command-line tools or credentials: Read is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: mcp__plugin_origin_origin__get_page, mcp__plugin_origin_origin__search_pages, mcp__plugin_origin_origin__get_page_links, Bash.

Does Read access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Read safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Read use?

Read is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Read use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Read?

Skills that share tags, products or a category with Read: LLM Wiki (Yeachan-Heo/oh-my-claudecode, 40k stars), Wiki Query (paperclipai/paperclip, 98k stars), Paperclip Distill (paperclipai/paperclip, 98k stars) and Wiki Lint (paperclipai/paperclip, 98k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Read?

davepoon (a GitHub user) maintains it in davepoon/buildwithclaude, which has 3,601 GitHub stars. The repository holds 246 skills in this directory. The repository was last updated on October 6, 2026.

Source: davepoon/buildwithclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.