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/element-reusenpx skills add vindm/dotclaude --skill element-reusegit 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 | $0.00087 | $0.01261 |
| Opus 5 | $0.00044 | $0.00630 |
| Sonnet 5 | $0.00017 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
element-reuse 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Element reuse (Gate A)
When you reuse an existing user-visible element on a new surface, you risk shipping the same intent into a context it wasn't authored for. The canonical scenario: a greeting string lives in the codebase, authored for a first-touch wizard. A developer building a daily-home widget needs a greeting line, greps, finds it, reuses it. The diff looks clean — an existing key, the cheapest-looking change. The user then sees "Hi — I'm your assistant, let me show you around" every single morning. Lint passes (the import resolves), code review passes (the diff is fine in isolation), visual review of the surface alone passes (the copy "reads OK" if you don't know the journey). It's only visible if someone asks: what context was this authored for, and does it match this new surface? That question is this gate.
Run at both moments:
- Design time — Section 0a of the spec, for every existing element the spec proposes to reuse.
- Audit time — first action when any borrowed string/component is detected on the captured surface. This catches implementation drift: the spec said "fresh string authored for daily-driver", but the implementation reached for the nearest existing string to save time. The design-time gate saw new authorship; the audit-time gate catches the silent substitution.
Procedure
Step 1 — Locate the existing usage
Grep for the existing usage of the proposed element (a string key, a component import, a copy pattern), across this project's user-visible code directories (discover them at runtime — translation files, components, screens):
grep -rn "<exact-string-or-key>" <user-visible-code-dirs>
For each hit, capture: file:line, the surface it fires on (read the surrounding code to confirm), the role it plays there (intro / confirmation / CTA / status / error), and when the user sees it.
No grep evidence → no finding. "I think this is reused somewhere" without a file:line is not a verdict-eligible claim.
Step 2 — Classify both contexts
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 · 76 lines · 87 tokens per session scan A bcaae33c8ae5
element-reuse is a skill published in the GitHub repository vindm/dotclaude (1 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 1,261 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.