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 skills add siva01c/claude-plugins --skill drygit clone --depth 1 https://github.com/siva01c/claude-pluginsWrote 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/siva01c/claude-plugins/dry)<a href="https://agentmods.dev/skills/siva01c/claude-plugins/dry"><img src="https://agentmods.dev/badge/skills/siva01c/claude-plugins/dry/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.
<a href="https://agentmods.dev/skills/siva01c/claude-plugins/dry"><img src="https://agentmods.dev/badge/skills/siva01c/claude-plugins/dry.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00116 | $0.00740 |
| Opus 5.5 | $0.00046 | $0.00296 |
| Sonnet 5.5 | $0.00023 | $0.00148 |
| Haiku 4.5 | $0.00012 | $0.00074 |
Grade A, and why
dry 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 17d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DRY Review
DRY is about knowledge, not text. A finding is the same decision encoded in two or more places that have to change together — so that changing one and forgetting the other is a bug waiting to happen. Two blocks of similar-looking code that encode different decisions are not duplication, and merging them would couple things that should vary independently.
What to look for
- Rules and validation — the same allow-list, regex, limit or permission check in a form, an API endpoint and a CLI command.
- Constants and magic values — a status name, a timeout, a URL, a field name or a path spelled out in several files instead of defined once.
- Parsers and formats — two hand-written parsers or serializers for the same file, header, JSON shape or command output.
- Protocol details — the same auth header, retry policy, pagination loop or error mapping re-implemented per client.
- Copied functions — a helper copied into a second module with small edits, where both copies are still meant to behave the same.
- Docs and code — a procedure described in two documents, or a value documented in a README and hard-coded elsewhere, when both must stay in sync.
In a diff, check first whether the change adds a copy of something that already exists in the codebase: search for the key identifiers, strings and regexes it introduces.
Not a finding
- Similar code that encodes different decisions, or would diverge on the next change.
- Two or three lines of glue, test setup or boilerplate the framework expects.
- Tests that restate expected values on purpose.
- Duplication across separately released projects (a public library and a private monorepo) that are deliberately kept standalone.
- Generated, vendored and lock files.
Severity
high— the copies have already drifted: they disagree today, and you can show the input that behaves differently in each.medium— default: the copies are identical now but must change together, and nothing ties them.low— small repeated literals or helpers where a mismatch would be cosmetic.
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.
- 17d ago First seen · 67 lines · 116 tokens per session scan A b756c4f2d825
dry is a skill published in the GitHub repository siva01c/claude-plugins (16 stars, last pushed 17d ago), licensed MIT. It adds 116 tokens to every session and 740 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
rubber-duck
Invoke a Rubber Duck Reviewer subagent to independently critique plans and implementations before proceeding. Use when the agent is about to implement a non-trivial plan (multi-file changes, architectural decisions, security-sensitive logic, database schema changes), after completing a self-contained unit of work…
code-review-checklist
Genera un checklist de revisión de código personalizado para cualquier pull request basado en el lenguaje, tipo de cambio y nivel de riesgo. Úsalo cuando te pidan revisar código, verificar un PR, revisar un pull request o generar un checklist de revisión de código. Produce un checklist enfocado con verificaciones…
best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
pr-description-writer
Redacta una descripción de pull request clara y estructurada a partir de un diff de git, resumen de rama o lista de commits. Úsalo cuando te pidan escribir una descripción de PR, redactar una solicitud de cambios o documentar cambios de código. Produce una descripción con resumen, motivación, cambios realizados, pasos…
resolve-pr-comments
Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using the rationale recalled from past Claude Code transcripts). Use when the user asks to "resolve PR comments", "fix review comments", "address…
review-code
Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps and low-value tests by running internal reviews and a peer review in parallel and returning combined findings. Single-concern with a type argument, or full review with no argument. Use when the…