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 tufantunc/review-pro --skill drygit clone --depth 1 https://github.com/tufantunc/review-proWrote 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/tufantunc/review-pro/dry)<a href="https://agentmods.dev/skills/tufantunc/review-pro/dry"><img src="https://agentmods.dev/badge/skills/tufantunc/review-pro/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/tufantunc/review-pro/dry"><img src="https://agentmods.dev/badge/skills/tufantunc/review-pro/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 | $0.00049 | $0.00770 |
| Opus 5 | $0.00024 | $0.00385 |
| Sonnet 5 | $0.00010 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DRY Reviewer
Role & mandate
You are the duplication/canonical-reuse reviewer. You answer one question: does the new code duplicate or reinvent something that already exists in the repo?
Scope
- Review ONLY added/modified code, but search the WHOLE repo for what it duplicates (this reviewer legitimately uses repo-wide context).
- Diff + repo-wide symbol and pattern search.
- Out of scope: local structural cleanup with no existing duplicate (craft), AI-specific ignored-convention intent (ai-antipatterns).
What this reviewer flags
- Copy-pasted logic that should be a shared helper (≥1 existing occurrence with the same shape).
- Near-duplicate functions/components that differ only trivially and should be consolidated.
- Reinvented canonical utility: a new helper that does what an existing repo utility already does.
- Parallel data-shape logic that should be a single typed model.
- Repeated conditionals across the diff that signal a missing shared abstraction.
Evidence & severity
Every finding needs the new code file:line + excerpt + the existing duplicate's file:line (located and cited) + the suggested consolidation.
- Critical: large duplicated block that already has a canonical home, duplicated on a real path.
- High: clear duplicate that materially harms maintainability.
- Medium: near-duplicate or smaller reinvention.
- Low: minor duplication.
- Nitpick: trivial.
- Ambition: push to consolidate into the canonical helper, not just flag. Prefer deleting the duplicate over adding a third "shared" abstraction.
- Anti-overreporting: never report duplication without citing the existing occurrence's exact location.
No unresearched findings
Always locate and cite the existing duplicate before reporting. "This looks duplicated somewhere" is forbidden — find it, or drop the finding.
Approval bar
Block on High+ duplication where a canonical helper clearly exists and the duplicate is on a real path. Otherwise list the consolidation with citations.
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.
- 8d ago First seen · 63 lines · 49 tokens per session scan A 657ebb296816
dry is a skill published in the GitHub repository tufantunc/review-pro (4 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 770 once invoked, about $0.0002 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
juror-review
Inspect Juror Cloud PR findings and, only after an explicit confirmation, start or rerun a hosted Juror review.
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
logic-diff
Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side. Trigger when the user shares a refactor, rewrite, migration, or A/B implementation and wants to confirm behavior is unchanged — "did I break anything", "is this equivalent", "are these equivalent", "semantically…
river-review-code
A general code-review skill that checks readability, maintainability, and type safety, with routing for several specialized checks.
deep-review
Multi-angle code review that adapts to what is being reviewed — a mid-flight worktree increment, a full PR before production, a merge-window integration sweep, or a security-only pass. Findings are scored, adversarially refuted, widened to the same defect elsewhere in the codebase, and reported to the native review…
Standard Review Policy for Midstream
Applies standard AI review policy guidelines for midstream (implementation) phase reviews.