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/baseballyama/eslint-plugin-postgresql/full-code-reviewnpx skills add baseballyama/eslint-plugin-postgresql --skill full-code-reviewgit clone --depth 1 https://github.com/baseballyama/eslint-plugin-postgresqlWhat 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 | $0.00082 | $0.02389 |
| Opus 5 | $0.00041 | $0.01195 |
| Sonnet 5 | $0.00016 | $0.00478 |
| Haiku 4.5 | $0.00008 | $0.00239 |
Grade A, and why
full-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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full code review
Before opening a PR — or before merging your own — review the branch as if you were a maintainer who didn't write it. The author's view is "what I built"; the maintainer's view is "what this costs forever." This skill walks the second view.
The skill is collaborative: each phase produces a finding, you and the user agree on what to do about it, and only then do you move to the next phase. Do not batch all phases and dump the result at the end.
Step 0 — Establish the baseline
Decide what you're comparing against and what the diff actually contains.
# Determine the base branch (in priority order):
# 1. User explicitly said "compare against X" → use X
# 2. PR exists → gh pr view <num> --json baseRefName
# 3. Default → origin/main (or the project's primary branch)
git fetch origin
git diff --stat ${BASE}...HEAD
git log --oneline ${BASE}...HEAD
git diff --name-only ${BASE}...HEAD
Categorize the changed files (use whatever buckets fit the project):
- Public API surface (entry points, type exports)
- Internal implementation
- Tests
- Documentation
- Build / CI / tooling
- Dependencies (lockfile, package manifests)
Report to user: which base branch you're using, the diff size, and the categorization. If the diff is huge (thousands of lines or many unrelated buckets), flag that this PR may need to be split — and confirm whether to continue.
Phase 1 — Why does this change exist?
The hardest review question is "should this even ship?" Before judging the code, make sure the change has a real reason to exist.
Pull what's available:
- PR description, linked issues, commit messages
- Any design discussion the user can paste in
- Connect to the
CLAUDE.mdpolicies — especially "one way to do one thing"
Confirm with the user:
- Problem: what is the user-facing problem this solves?
- Audience: who specifically is affected? (new users, advanced users, a specific integration?)
- Alternatives: was a smaller, doc-only, or "use the existing path" answer considered?
- Scope fit: does this stay inside this project's stated scope?
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 · 254 lines · 82 tokens per session scan A 8a5827852b00
full-code-review is a skill published in the GitHub repository baseballyama/eslint-plugin-postgresql (11 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 2,389 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…