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/dryvist/claude-code-plugins/validate-readmenpx skills add dryvist/claude-code-plugins --skill validate-readmegit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat 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 | $0.00072 | $0.00820 |
| Opus 5 | $0.00036 | $0.00410 |
| Sonnet 5 | $0.00014 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
validate-readme 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate README
Run a comprehensive audit of all README.md files in the current repository.
Usage
/validate-readme
Steps
1. Find all README files
Find all README*.md files in the repository, excluding .git/ and .claude/
directories.
2. Validate each README
For each README found, check:
- Required sections present (from
.readme-validator.yamlor defaults) - Installation section contains at least one code block
- Optional sections present (warnings only)
Badge URL reachability may be checked on-demand using WebFetch for any badge images found in the README.
3. Score quality
Section presence is a floor, not a measure of quality — a README can carry every
required heading and still tell a reader nothing. Score each README 0-6 against
these checks and report the score alongside the pass/warn status. The lowest-
numbered failing check is the file's gap: the one thing most worth fixing.
| # | Check | Pass condition |
|---|---|---|
| 1 | Exists | README.md present at the directory root |
| 2 | Purpose paragraph | First non-frontmatter, non-badge, non-heading paragraph is prose stating what the project does — at least 30 and at most 500 characters, not starting with a list bullet |
| 3 | Quickstart | A ## Quick Start, ## Install, ## Installation, ## Getting Started, or ## Setup section appears within the first 80 lines |
| 4 | Usage examples | A ## Usage, ## Examples, or ## Example section — or the Quickstart — contains a code block of at least 3 lines |
| 5 | License | A ## License section, or a license badge linking to LICENSE / LICENSE.md |
| 6 | Length | Between 30 and 400 non-blank lines — below is a stub, above is a manual that should be split out |
Check 2 is the one that most often fails on a README that passes section validation, and it is usually the most valuable to fix: a reader who cannot tell what a project does from its opening paragraph will not read the rest.
Scope note: repo description and CLAUDE.md quality travel with README quality
but are not README checks. Leave them to the tools that own those files —
claude-md-improver (claude-md-management) covers CLAUDE.md.
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 · 96 lines · 72 tokens per session scan A 119a5db371a8
validate-readme is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 72 tokens to every session and 820 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
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
dragonruby
This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
mcp-server
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…
ratatui-ruby
This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…