A project-level tool for extending an existing coding-agent skill. It lists available skills, checks for existing extensions, and creates or opens the files needed for a custom version.

Use it when you want to customize how a plugin skill behaves in one project. It helps start or continue an extension for a skill or agent.

It removes the need to find the right extension files and work out where they belong. It also checks for older extension names and combines project, user, and default settings.

auto-extend — Skill for Claude Code by Jerry0022/dotclaude

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.

Any agent

npx skills add Jerry0022/dotclaude --skill auto-extend

Clone the repo

git clone --depth 1 https://github.com/Jerry0022/dotclaude

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 18 skills, 12 agents, 9 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-extend/github.svg)](https://agentmods.dev/skills/jerry0022/dotclaude/auto-extend)

Your own site

<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-extend"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-extend/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-extend"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-extend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,193 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.01193
Opus 5.5	$0.00021	$0.00477
Sonnet 5.5	$0.00010	$0.00239
Haiku 4.5	$0.00005	$0.00119

Measured 12d ago against content hash ea941b991ea7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-extend 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.

The scan reads SKILL.md. This mod also ships 1 executable file (step0-reference-only.test.js), 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/devops/skills/auto-extend/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Extend Skill — Interactive Extension Scaffolding

Scaffold or adapt a project-level extension for any devops skill.

Step 0 — Load Extensions

Injected by the override loader ([skill-overrides] block); none shown → none exist.

{project} = the nearest parent with .git/ or .claude/; all extension paths below are relative to it.

Step 1 — Determine target skill

Use the skill name from the argument; otherwise list the plugin's skills/ (and agents/ extensions) and ask via AskUserQuestion which one to extend.

A pre-PR-2 name (ship, fix, run-backlog, promote, … — table in {PLUGIN_ROOT}/hooks/lib/skill-names.js) is translated to the skill that owns it now (do-ship, auto-fix, do-run, do-ship, …). A PR-3 retired name (RETIRED in the same table: setup-readme, auto-usage, claude-strict) is no skill: say so and name its deep-knowledge doc (RETIRED[name].doc). An extension under that old name keeps applying only where the doc says so (readme-standards, usage and strict name .claude/skills/<old>/reference.md as an override). A name that matches nothing → say so and ask again.

Step 2 — Check for an existing extension

Look for reference.md (and a legacy SKILL.md) in {project}/.claude/skills/{skill-name}/ and in the skill's pre-PR-2 dir(s) (ship/ for do-ship, the folded skill names for do-run / do-ship modes). An extension found only under the old name is reported as existing ("still loaded as fallback"); before editing it, offer to git mv it to the new name. A legacy SKILL.md override is reported as deprecated: it is still read as a fallback, but Claude Code loads a SKILL.md there as a user skill of its own (a bare /{skill-name} beside the plugin's). Offer to move its content into reference.md (git mv when no reference.md exists yet, else merge the text into it and delete the old file).

Exists → show which files exist and their content, then ask whether to edit one, add the missing one, or abort; apply the requested edits.
Missing (or a single missing file) → Step 3 for what is missing.

Read the full file on GitHub · 107 lines

Files

What ships with it

2 files 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.

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.

12d ago Changed ea941b991ea7
16d ago Changed · +7 lines ec013c24b32f
1mo ago Changed · -46 lines f1615ab0e586
1mo ago Changed 2741faf5e756
1mo ago First seen · 146 lines · 52 tokens per session scan A 9315e7fbdf58

Subscribe to this mod's changes

auto-extend is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 52 tokens to every session and 1,193 once invoked, about $0.0002 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 2026-09-24.

Building agents

auto-extend next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
auto-extendJerry0022/dotclaude	Skill	6	11d ago	MIT	A	52	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code