update

update is a skill for Claude Code from eunji-jessi-jung/reef. It costs 7 tokens per session (6,468 once invoked), scanned A, original, Apache-2.0.

An update tool for a Reef, a structured knowledge base built from source material. It re-checks source code, extracts updated specifications, detects changes, and creates a report for review.

In plain words
What is it for?
Use it to re-index sources, identify stale documents, review proposed updates, and optionally apply all changes automatically.
Why use it?
It helps keep generated knowledge-base documents from becoming out of date as their source files change.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the reef plugin — 11 skills, 1 agent shipped together

Good fit Use it to re-index sources, identify stale documents, review proposed updates, and optionally apply all changes automatically.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add eunji-jessi-jung/reef
Claude Code
/plugin install reef

Made for: Claude Code.

Or install reef, the plugin that ships this one along with the rest of its 11 skills, 1 agent.

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 update

README.md
[![agentmods](https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/update/github.svg)](https://agentmods.dev/skills/eunji-jessi-jung/reef/update)
Your own site
<a href="https://agentmods.dev/skills/eunji-jessi-jung/reef/update"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/update/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 update

Your own site · 80×15
<a href="https://agentmods.dev/skills/eunji-jessi-jung/reef/update"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,468 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 $0.00007 $0.06468
Opus 5 $0.00003 $0.03234
Sonnet 5 $0.00001 $0.01294
Haiku 4.5 $0.00001 $0.00647

Measured 12d ago against content hash 75ef3077290c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

update 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 12d 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/update/SKILL.md · 563 lines

How it starts

The opening of the file, as written. The whole thing — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/reef:update

Pull latest source code, re-extract specs, detect what changed, and produce an update report for human review. This is the "keep your reef alive" skill. /reef:health reports staleness; /reef:update fixes it.

Default mode is human-reviewed. Changes are presented as a curated report. You decide what to apply. Use --auto to apply everything without prompting.

Setup

Read these references before doing anything else:

  • ${CLAUDE_PLUGIN_ROOT}/references/artifact-contract.md
  • ${CLAUDE_PLUGIN_ROOT}/references/methodology.md

Voice

Curious Researcher. Present-participle narration. No emojis. No exclamation marks.

Procedure

0. Check for an unfinished update report

Before doing anything else, check if .reef/update-report.json exists.

If it exists and has items with "status": "pending":

Count applied, pending, and skipped items. Then check staleness: compare the report's source_index_at against the current modification times of source files on disk (spot-check 5-10 files from the source index). If any have changed since the report was generated, the report is stale.

Report is fresh (sources unchanged):

Found an unfinished update report from {date}.
  Applied: N items | Pending: M items | Skipped: K items

Options:
  1. Resume — review remaining M items
  2. Regenerate — re-scan sources and build a fresh report

Report is stale (sources changed since generation):

Found an unfinished update report from {date}.
  Applied: N items | Pending: M items | Skipped: K items

Warning: sources have changed since this report was generated.
The report may be incomplete or outdated.

Options:
  1. Regenerate — build a fresh report from current sources (recommended)
  2. Resume anyway — apply remaining items (may miss new changes)
  3. Discard — delete the old report and start fresh

On Resume: skip to Step 7 (present report and review loop) with the existing report. On Regenerate or Discard: delete update-report.json and proceed from Step 1.

Read the full file on GitHub · 563 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. 12d ago First seen · 563 lines · 7 tokens per session scan A 75ef3077290c

Subscribe to this mod's changes

update is a skill published in the GitHub repository eunji-jessi-jung/reef (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 6,468 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens