adapto-microcopy

adapto-microcopy is a skill for Claude Code from adaptocms/adapto-cms-agent-skills. It costs 69 tokens per session (1,697 once invoked), scanned A, original, MIT.

A tool for managing short interface text such as navigation labels, button text, errors, and empty states as language entries in Adapto.

In plain words
What is it for?
Use it to seed starter interface text for a new project or find existing hardcoded strings and create a file-and-line replacement guide.
Why use it?
It replaces scattered hardcoded interface strings with named entries and provides a review step before new entries go live.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the adapto plugin — 16 skills, 3 agents, 1 hook shipped together

Good fit Use it to seed starter interface text for a new project or find existing hardcoded strings and create a file-and-line replacement guide.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adaptocms/adapto-cms-agent-skills/adapto-microcopy
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 adaptocms/adapto-cms-agent-skills --skill adapto-microcopy
Clone the repo
git clone --depth 1 https://github.com/adaptocms/adapto-cms-agent-skills

Made for: Claude Code.

Or install adapto, the plugin that ships this one along with the rest of its 16 skills, 3 agents, 1 hook.

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 adapto-microcopy

README.md
[![agentmods](https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-microcopy/github.svg)](https://agentmods.dev/skills/adaptocms/adapto-cms-agent-skills/adapto-microcopy)
Your own site
<a href="https://agentmods.dev/skills/adaptocms/adapto-cms-agent-skills/adapto-microcopy"><img src="https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-microcopy/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 adapto-microcopy

Your own site · 80×15
<a href="https://agentmods.dev/skills/adaptocms/adapto-cms-agent-skills/adapto-microcopy"><img src="https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-microcopy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,697 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 $0.00069 $0.01697
Opus 5 $0.00034 $0.00848
Sonnet 5 $0.00014 $0.00339
Haiku 4.5 $0.00007 $0.00170

Measured 9d ago against content hash 0479b3a8951b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adapto-microcopy 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 9d 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.

plugin/skills/adapto-microcopy/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

adapto:microcopy

Manages a project's micro copy — the short UI strings (nav, buttons, labels, validation, empty/loading states, footer) stored in Adapto as key/value/language entries. Two modes:

  • init — seed a curated, project-aware starter set of UI strings with on-brand values (greenfield).
  • extract — scan an existing frontend for hardcoded UI strings, create entries, and emit a file:line → key replacement guide (it never rewrites your source).

⚠️ Micro copy has no draft state — entries go live on create. So the plan-approval below is the only safety gate (there's no draft-review net like the content skills have). Review the plan carefully.

When to use

  • init: "seed UI strings", "starter microcopy", "set up my UI text".
  • extract: "extract microcopy", "pull the hardcoded strings from my site into Adapto".

When not to use

  • Translating microcopy into another language → adapto:translate.
  • Content (articles / pages / collection items) → adapto:content-seed.
  • Just checking the environment → adapto:doctor.

Inputs

  • Modeinit or extract. Infer from the request; if ambiguous, ask which.
  • Project context for voice (.adapto/project.md cache or adapto collections get-by-slug _adapto_project_config --json); absent → neutral defaults.
  • Tenant language (adapto auth orgs --json).
  • For extract: a scaffolded frontend in the current directory.
  • Key convention: dot-namespaced (nav.home, button.submit, form.email.label) — both modes use it.

Outputs

  • Created micro copy entries (key/value/language); a report of created + skipped.
  • extract only: a replacement guide at .adapto/microcopy-extract-<date>.md mapping file:line → key, so you can wire the read-client lookups yourself. Source is never modified.
  • Next step: suggest adapto:translate to localize the micro copy into another enabled language; for extract, also wiring the read-client lookups from the guide; for init, extract mode to catch any hardcoded strings already in the frontend.

Read the full file on GitHub · 101 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. 9d ago First seen · 101 lines · 69 tokens per session scan A 0479b3a8951b

Subscribe to this mod's changes

adapto-microcopy is a skill published in the GitHub repository adaptocms/adapto-cms-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,697 once invoked, about $0.0003 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.