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.
npx agentmods add skills/viknesh20-20/claude-code-tool-kit/microcopynpx skills add viknesh20-20/claude-code-tool-kit --skill microcopygit clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWrote 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.
[](https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/microcopy)<a href="https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/microcopy"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/microcopy.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00050 | $0.01945 |
| Opus 5 | $0.00025 | $0.00972 |
| Sonnet 5 | $0.00010 | $0.00389 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade A, and why
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/microcopy
Write the small strings that decide whether users figure your product out — or churn. Bad copy makes good visuals fail; good copy carries average visuals.
When to use
- Designing or reviewing any user-facing text — buttons, errors, empty states, tooltips, confirmations, form labels, onboarding.
- After a UX review flagged unclear messaging.
- When a feature ships with placeholder strings ("Submit," "Error," "Loading…") and needs real ones.
- When localizing — the source strings need to be localizable in the first place.
Operating method
1. Establish voice
Read 5–10 existing strings from the product before writing new ones. Identify:
- Tone — professional / friendly / playful / clinical. Most B2B is professional-with-warmth; consumer varies wildly.
- Person — second person ("Save your changes") almost always. First-person plural ("We saved your changes") for system updates only.
- Verb usage — direct ("Save"), polite ("Please save"), or playful ("Stash it"). Pick one and stick with it.
- Punctuation — sentence case vs title case for buttons. Periods at end of error messages or not.
- Emoji — used or not. (Default: not. Add only if the product already uses them.)
If no existing strings exist, default to: direct, second person, sentence case for buttons, periods on full sentences, no emoji.
2. Apply the four rules
Verbs over nouns on buttons. Buttons do something. Use the verb.
| Bad | Good |
|---|---|
| Submit | Send invite |
| OK | Save changes |
| Confirmation | Confirm payment |
| Settings | Open settings |
Specific errors with recovery. Tell the user what went wrong AND what to do.
| Bad | Good |
|---|---|
| Invalid input | Email must include an @ symbol |
| Error | Couldn't reach the server. Check your connection or retry. |
| Try again | Card declined — try a different card |
| Failed | Two-factor code expired — request a new one |
Empty states have CTAs. Don't leave the user stranded with "No results."
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.
- 3d ago First seen · 199 lines · 50 tokens per session scan A a609d2500d88
microcopy is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 1,945 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.
Other skills, from other repositories
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
security-review
Review trust boundaries, auth/authz, injection, secrets, filesystem/network exposure, dependencies, and exploitability without pretending a shallow lint is an audit.