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/code-payments/code-android-app/dep-reviewnpx skills add code-payments/code-android-app --skill dep-reviewgit clone --depth 1 https://github.com/code-payments/code-android-appWhat 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 | $0.00031 | $0.01457 |
| Opus 5 | $0.00015 | $0.00728 |
| Sonnet 5 | $0.00006 | $0.00291 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
dep-review 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Update Review
Review a Dependabot pull request to evaluate the dependency update for breaking changes, deprecations, and required code modifications.
Input
Parse $ARGUMENTS for a PR reference:
#803or803— PR numberhttps://github.com/code-payments/code-android-app/pull/803— full URL (extract the number)
If no argument is provided, stop and ask the user for a PR number.
Steps
Step 1 — Fetch PR details
gh pr view <number> --repo code-payments/code-android-app --json title,body,files,headRefName,baseRefName,diff
Extract:
- Title — Dependabot titles follow:
Bump <group-or-artifact> from X.Y.Z to A.B.C - Body — Contains Dependabot's auto-generated release notes, changelog links, and compatibility scores
- Changed files — Typically
gradle/libs.versions.tomland possiblybuild.gradle.ktsfiles - Diff — The actual version change
If the PR is not a Dependabot PR (author is not dependabot[bot] or title doesn't match the pattern), warn the user but continue — they may want to review a manual dependency bump.
Step 2 — Parse the version change
From the diff of gradle/libs.versions.toml, identify:
- Catalog key — the version alias (e.g.,
grpc = "1.68.0"→grpc) - Old version — the version being replaced
- New version — the version being introduced
- Affected libraries — all
[libraries]entries that reference this version alias
If multiple versions are bumped (grouped Dependabot PR), repeat the analysis for each.
Present a summary table:
| Catalog Key | Library | Old Version | New Version | Bump Type |
|---|---|---|---|---|
grpc |
io.grpc:grpc-okhttp |
1.68.0 | 1.69.0 | minor |
Bump type classification:
- patch (0.0.x) — bug fixes, lowest risk
- minor (0.x.0) — new features, backward compatible
- major (x.0.0) — potential breaking changes, highest risk
Step 3 — Fetch release notes / changelog
For each dependency being bumped:
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 · 181 lines · 31 tokens per session scan A 42e66e7b2359
dep-review is a skill published in the GitHub repository code-payments/code-android-app (23 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,457 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…