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/vindm/dotclaude/persona-testingnpx skills add vindm/dotclaude --skill persona-testinggit clone --depth 1 https://github.com/vindm/dotclaudeWhat 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 | $0.00074 | $0.01243 |
| Opus 5 | $0.00037 | $0.00622 |
| Sonnet 5 | $0.00015 | $0.00249 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
persona-testing 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 2d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona testing
A deny-list catches binary phrase violations and the reuse gate catches context-mismatch reuse, but a string can pass both and still feel wrong: written for day-1 enthusiasm it reads condescending on day 30; written in customer-service register it reads performative when the assistant is meant to feel like a peer; written for a stranger it reads patronizing to a user who already knows the app. These aren't specific phrases — they're voice-register failures spread across many words. Three orthogonal tests catch them.
Run this at both moments:
- Design time — every proposed copy element in the spec passes the triad before the spec is approved.
- Audit time — first action when any visible copy element is found on the audited surface; verify the string in source, apply all three tests, and the REWRITE verdict binds regardless of what the spec said. This rerun is the only thing that catches implementation drift: an engineer swapping "Continue" for "Next", a translation file extended by pattern-matching from an adjacent first-touch surface, or an LLM-shaped pipeline emitting a customer-service register that was never in the spec.
The three tests
Each is orthogonal. A string passes only if all three PASS — two-of-three ships drift.
Test 1 — Frequency-jaded ("day-30")
"Would this string read OK if the user saw this exact string on day 30? Day 60? Day 365?"
A first-touch string fails instantly: "Hi — I'm your assistant" on day 30 is repetition, not welcome. An evergreen status string passes: a quiet-state line works every day it's true. Catches strings authored for new-user emotional context and shipped to surfaces the user revisits regularly.
Match the framing to the product's usage pattern, derived at runtime. For a once-per-user flow (a checkout) the right framing is "did this read OK to a user under cognitive load" rather than "on the 30th rerun". For other product shapes, swap the whole triad for the fitting one — a CLI tool: first-run / power-user / regression-debugger; a doc site: skimmer / focused-learner / reference-checker; a B2B tool: trial-evaluator / power-admin / new-team-member. Pick the triad that fits this project's reader.
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.
- 2d ago First seen · 61 lines · 74 tokens per session scan A a40e5aff77c8
persona-testing is a skill published in the GitHub repository vindm/dotclaude (1 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 1,243 once invoked, about $0.0004 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
claude-md-review
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
code-reviewer
Automatic code quality and best practices analysis. Use proactively when files are modified, saved, or committed. Analyzes code style, patterns, potential bugs, and security basics. Triggers on file changes, git diff, code edits, quality mentions.
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
test-generator
Automatically suggest tests for new functions and components. Use when new code is written, functions added, or user mentions testing. Creates test scaffolding with Jest, Vitest, Pytest patterns. Triggers on new functions, components, test requests, testing mentions.
api-documenter
Auto-generate API documentation from code and comments. Use when API endpoints change, or user mentions API docs. Creates OpenAPI/Swagger specs from code. Triggers on API file changes, documentation requests, endpoint additions.
readme-updater
Keep README files current with project changes. Use when project structure changes, features added, or setup instructions modified. Suggests README updates based on code changes. Triggers on significant project changes, new features, dependency changes.