agentmods.dev

al-folio: Agent for Claude Code

.github/agents/customize.agent.md

customization_agent is an agent for Claude Code from alshedivat/al-folio. It costs 17 tokens per session (346 once invoked), scanned A, original, MIT.

A coding assistant for customizing al-folio version 1.x, a Jekyll starter for academic and personal websites, together with its plugins. It guides changes to site settings, content, data, and intentional local overrides.

In plain words
What is it for?
Use it to adjust site configuration, metadata, data files, pages, posts, projects, publications, assets, and plugin-owned behavior that needs to be routed elsewhere.
Why use it?
It helps customize a site without accidentally editing files owned by a separate plugin. It also provides guidance for checking whether local overrides are still needed.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

This is alshedivat/al-folio's own configuration. It tells Claude Code how to work on al-folio 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 al-folio configures →

not rated 16krepo +22 2d ago A scan 17 tokens original MIT
View source ↗ alshedivat/al-folio alshedivat.github.io
About the project

al-folio is a Jekyll starter for building academic websites, personal sites, and portfolios. It is used by academics who want a responsive site based on independently versioned plugin components.

alshedivat/al-folio · 16,309 stars · on GitHub · alshedivat.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to alshedivat/al-folio. 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/alshedivat/al-folio/main/.github/agents/customize.agent.md
Clone the repo
git clone --depth 1 https://github.com/alshedivat/al-folio

Made for: Claude Code.

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 customization_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/alshedivat/al-folio/customize/github.svg)](https://agentmods.dev/agents/alshedivat/al-folio/customize)
Your own site
<a href="https://agentmods.dev/agents/alshedivat/al-folio/customize"><img src="https://agentmods.dev/badge/agents/alshedivat/al-folio/customize/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 customization_agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/alshedivat/al-folio/customize"><img src="https://agentmods.dev/badge/agents/alshedivat/al-folio/customize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 346 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 $0.00017 $0.00346
Opus 5.5 $0.00007 $0.00138
Sonnet 5.5 $0.00003 $0.00069
Haiku 4.5 $0.00002 $0.00035

Measured 2mo ago against content hash 636a75019977, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

customization_agent 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 2mo 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.

.github/agents/customize.agent.md · 52 lines

What it actually says

You are a customization assistant for al-folio v1.x.

Mission

Help users customize their site while respecting v1 ownership boundaries.

Boundary Model

  • al-folio starter: docs, content, config wiring, integration and visual checks.
  • al-* plugins: runtime feature behavior and component assets.

If a request changes runtime behavior, route to the owning plugin repo instead of patching starter internals.

User Guidance Priorities

  1. Keep explanations simple for non-expert users.
  2. Prefer editing _config.yml, content collections, and data files.
  3. Avoid monolith-era guidance that assumes starter owns _includes/_layouts/_sass runtime internals.
  4. When retaining local overrides of plugin-owned files, run the override audit and acknowledge reviewed overrides.

Key Starter Files

  • _config.yml
  • _data/*.yml
  • _pages/, _posts/, _projects/, _news/, _teachings/
  • Gemfile
  • README.md
  • docs/INSTALL.md, docs/CUSTOMIZE.md, docs/FAQ.md, docs/CONTRIBUTING.md, docs/BOUNDARIES.md

Validation

Use the validated command set in AGENTS.md.

For local overrides, include:

bundle exec al-folio upgrade overrides audit

Escalation

If user requests a feature that should live in a plugin:

  • identify likely owner plugin repo,
  • explain why,
  • provide starter wiring/docs changes only in this repo.
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. 2mo ago First seen · 52 lines · 17 tokens per session scan A 636a75019977

Subscribe to this mod's changes

customization_agent is an agent published in the GitHub repository alshedivat/al-folio (16,309 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 346 once invoked, about $0.0001 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 2026-08-30.

Frontendacademicacademic-websitejekylljekyll-themepersonal-websiteportfolio-website
Related

customization_agent compared with agents from other repositories

customization_agent next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
customization_agentalshedivat/al-folioAgent16k2d agoMITA17Claude Code
paper-auditorfcakyon/phd-skillsAgent43826d agoMITA63Claude Code
implementbahayonghang/academic-writing-skillsAgent5402d agononeA28Claude Code
stats-validatorMarazii/research-co-pilotAgent145mo agoMITA93Claude Code
data-cruncherMarazii/research-co-pilotAgent145mo agoMITA82Claude Code
git-committerMexregkan/claude-for-researchersAgent542mo agoMITA82Claude Code
pipeline-auditorMexregkan/claude-for-researchersAgent542mo agoMITA0Claude Code