JustHandled Labs
Menu
FIELDNOTES / AGENT WORKFLOWS

Claude Code mods
do not replace skills.

They change a different part of the experience. Here’s how to decide whether you need one—and what to check before you install it.

Choose the layer: a skill guides the task; a mod changes Claude Code behavior. Combine them only when the job needs both.
A useful distinction, not a safety rating. Both need appropriate review.

Your agent keeps leaving test results out of the handoff. Do you need a better checklist, or a new panel watching the work? Those are different problems. The arrival of Claude Code mods is a good reason to ask which one you actually have.

Start with what is missing

A skill gives an agent reusable instructions for a task. It can also include reference material and scripts. That makes it suitable for a repeatable procedure: reviewing a document, preparing a report or following a testing checklist. A skill is not necessarily text-only, and its bundled code still deserves inspection. Anthropic’s skill documentation explains that structure.

A mod is executable JavaScript or TypeScript that runs inside Claude Code. It can add an interactive panel, change how parts of the interface appear, or intervene in tool calls. Anthropic documents support in the CLI and Claude Desktop’s Code tab, with differences elsewhere. Do not assume that a mod works in every app that can load a skill. Read the mods overview.

A checklist problem does not automatically need a panel

Consider a release checklist. If the agent keeps forgetting to include test results in its handoff, clearer skill instructions and an explicit output format are a reasonable first experiment. If the operator needs a persistent panel showing which checks ran and which are unresolved, a mod may be worth testing.

These hypothetical examples point to the decision: does the extra interface or event handling remove an obstacle you can name? A panel that nobody needs is still another thing to maintain.

Our recommendation

Keep the task procedure useful on its own. The interface can be optional. Your teammate should not need your favorite panel just to follow the release checklist.

Read the code before you invite it in

Mods run with your permissions and are not sandboxed. Their reach can include files, environment secrets, network access and session behavior. Before loading a candidate, Anthropic recommends inspecting its hooks and calls using:

claude plugin validate ./some-mod

The command describes capabilities without running the mod. Treat that as inspection evidence, not a certificate that the code is safe. Review the documented trust boundary.

Change one thing, then look at the result

Try the same task with the same inputs before and after your change. Keep a note of the model and host version, active extensions, output, failures and added permissions. Include an ordinary job and an awkward case where the agent should stop or ask. A polished demonstration rarely volunteers the awkward case.

If you change the model, the instructions and the mod together, a better result will not tell you which change helped. Vary one component first. Keep an unchanged control, and check repeat runs rather than relying on the best demonstration.

For teams already keeping baseline and skill-assisted observations across model releases, our paid Agent Skill Model-Release Regression Harness can help evaluate those supplied records. It needs Python 3.10+ and a compatible agent; it does not run the models or inspect mod code. A simple comparison sheet is a sensible starting point if you do not yet have that evidence.

Sharing it brings another job

Claude plugins can be shared as folders or archives, or distributed through a plugin marketplace. The installation and update route is not the same thing as the component’s runtime support. Before offering a package to anyone else, test the exact installation path and explain which parts work in which host. Anthropic’s publishing guide describes the available routes.

Name the friction first. If better instructions solve it, keep the skill. If the working environment needs to change, test a mod against that specific need. A busier setup is not automatically a better one.