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/agentic-dev3o/devx-plugins/code-reviewnpx skills add agentic-dev3o/devx-plugins --skill code-reviewgit clone --depth 1 https://github.com/agentic-dev3o/devx-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 | $0.00049 | $0.00899 |
| Opus 5 | $0.00024 | $0.00449 |
| Sonnet 5 | $0.00010 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
code-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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Target: $ARGUMENTS (optional PR number, branch, path, or diff scope)
Workflow
Progress checklist:
Code Review:
- [ ] Step 1: Identify review target
- [ ] Step 2: Gather change context
- [ ] Step 3: Evaluate the change
- [ ] Step 4: Separate findings from noise
- [ ] Step 5: Deliver findings-first review
Step 1: Identify Review Target
- If
$ARGUMENTSis empty and the request is about a PR, rungh pr listto show open PRs, then ask the user which PR to review. - If
$ARGUMENTSlooks like a PR number, rungh pr view <number>to capture the title, status, base branch, head branch, and summary. - Otherwise treat the target as local changes, a branch, a commit range, or a file path.
Step 2: Gather Change Context
- For PR review, run
gh pr diff <number>. - For local review, inspect
git diff,git diff --staged, or the diff for the requested range. - Read the changed files with surrounding context. Do not review the raw diff in isolation.
- Identify the scope: feature, bug fix, refactor, test, docs, or mixed.
- If
ghis unavailable or unauthenticated, say so clearly and fall back to the available local diff.
Step 3: Evaluate the Change
Review for:
- Correctness — edge cases, null or empty inputs, error handling, stale state, off-by-one logic, async races, retries, cancellation, and timeouts.
- Maintainability — naming, duplication, single responsibility, magic values, avoidable complexity, and consistency with nearby code.
- Performance — N+1 queries, repeated expensive work, render-loop costs, unnecessary allocations, and over- or under-used memoization.
- Type safety — missing narrowing, unchecked unions, overly broad types, and unclear public API return types.
- Testing — coverage for happy paths, failure paths, and the most likely regression cases.
- Security — auth gaps, injection risks, secret handling, unsafe parsing, XSS, SSRF, or CSRF when relevant.
Step 4: Separate Findings from Noise
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 · 107 lines · 49 tokens per session scan A f2692bddb1a7
code-review is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 49 tokens to every session and 899 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…