claude-init: Skill for Claude Code

.claude/skills/update/SKILL.md

update is a skill for Claude Code from yash-gadodia/claude-init. It costs 48 tokens per session (1,685 once invoked), scanned A, original, MIT.

A skill for re-analyzing a repository and refreshing its existing .claude configuration, which contains instructions and settings for AI-assisted development.

In plain words
What is it for?
Use it after stack, dependency, architecture, testing, CI, or directory changes to update configuration, agents, skills, rules, hooks, and related documentation.
Why use it?
It keeps documented project guidance aligned with changes in the codebase while preserving custom settings.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is yash-gadodia/claude-init's own configuration. It tells Claude Code how to work on claude-init itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-init configures →

Part of the claude-init plugin — 11 skills, 1 command, 7 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to yash-gadodia/claude-init. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yash-gadodia/claude-init/main/.claude/skills/update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yash-gadodia/claude-init

Made for: Claude Code.

Or install claude-init, the plugin that ships this one along with the rest of its 11 skills, 1 command, 7 agents.

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/yash-gadodia/claude-init/update.svg)](https://agentmods.dev/skills/yash-gadodia/claude-init/update)
Your own site
<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/update"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/update.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,685 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 $0.00048 $0.01685
Opus 5 $0.00024 $0.00843
Sonnet 5 $0.00010 $0.00337
Haiku 4.5 $0.00005 $0.00169

Measured 8d ago against content hash 8151e84d3803, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

.claude/skills/update/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update: Refresh AI-Native Config

Re-analyze the codebase and update the existing .claude/ configuration to match the current state.

Process

Step 1: Snapshot Current Config

Read and fingerprint every existing config file:

  • CLAUDE.md — extract sections, note any <!-- custom --> or <!-- generated --> markers
  • ARCHITECTURE.md — check if it exists and capture its Directory Structure section for drift comparison
  • agents/ — list all agents and their model/tool config
  • skills/ — list all skills and their paths: scopes (not just rules — skills can be path-scoped too)
  • rules/ — list all rules and their paths: scopes
  • settings.json — read hooks, permissions, and any outputStyle field
  • output-styles/ — list any custom output styles (generated tdd.md, user-added ones)
  • settings.local.json.example — check it exists so new contributors can bootstrap personal overrides

Step 2: Re-Analyze the Codebase

Run the same analysis as /claude-init (parallel subagents):

  • Stack detection (languages, framework, package manager, monorepo)
  • Architecture (DB, auth, API, state management)
  • Testing & CI (test framework, runner, CI/CD)
  • Conventions (commit style, linting, directory structure)

Step 2.5: Template Sync (catch stale generated config)

Codebase drift is not the only reason config goes stale — the templates themselves improve over time, and a project generated by an older claude-init keeps the old (sometimes buggy) output. /update must close that gap, because nothing auto-propagates: generated .claude/ files are static copies with no live link back to the templates.

Resolve the current templates the same way /claude-init does — first match wins:

  1. ${CLAUDE_SKILL_DIR}/../../../templates/ (running from a cloned repo)
  2. ~/.claude/claude-init-templates/ (global install)

If neither exists, skip this step (note it in the report so the user knows template-sync was unavailable) and continue with the codebase-drift diff.

Read the full file on GitHub · 128 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. 8d ago First seen · 128 lines · 48 tokens per session scan A 8151e84d3803

Subscribe to this mod's changes

update is a skill published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,685 once invoked, about $0.0002 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.