pubky-app: Skill for Claude Code

.agents/skills/pubky-code-review/SKILL.md

pubky-code-review is a skill for Claude Code, Codex from pubky/pubky-app. It costs 56 tokens per session (2,689 once invoked), scanned A, original, MIT.

A local code-review workflow that checks a change against the repository's documented architecture rules and quality standards. It reviews a branch, pull request, selected paths, or uncommitted changes without editing them.

In plain words
What is it for?
Use it to review diffs, audit changes, and check code against files such as AGENTS.md, .greptile/config.json, and the project's available checks.
Why use it?
It helps catch project-rule violations and quality problems before a pull request is opened. It also avoids manually deciding which changes should be reviewed when the repository state already provides the answer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code; installed under .agents/ (shared by several agents).

This is pubky/pubky-app's own configuration. It tells Claude Code and Codex how to work on pubky-app itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pubky-app configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pubky/pubky-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pubky/pubky-app/dev/.agents/skills/pubky-code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pubky/pubky-app

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pubky-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/pubky/pubky-app/pubky-code-review/github.svg)](https://agentmods.dev/skills/pubky/pubky-app/pubky-code-review)
Your own site
<a href="https://agentmods.dev/skills/pubky/pubky-app/pubky-code-review"><img src="https://agentmods.dev/badge/skills/pubky/pubky-app/pubky-code-review/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.

agentmods 80×15 button for pubky-code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/pubky/pubky-app/pubky-code-review"><img src="https://agentmods.dev/badge/skills/pubky/pubky-app/pubky-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,689 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.02689
Opus 5.5 $0.00022 $0.01076
Sonnet 5.5 $0.00011 $0.00538
Haiku 4.5 $0.00006 $0.00269

Measured 12d ago against content hash ee1af327a55c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pubky-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 12d 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.

.agents/skills/pubky-code-review/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local Code Review

Review a change against the project's rules with three focused read-only reviewers, a deterministic callouts pass, and the project's own checks when they are available. Print one status line once the scope is known, then the report. Do not narrate the steps in between.

Step 1 — Determine the scope

Work out what to review without asking when the answer is already known:

Signal Scope
The request or the skill argument names a branch, a PR number, one or more paths, or says local/uncommitted Use it
Uncommitted changes exist (git status --porcelain is non-empty) and nothing was named Local uncommitted changes
Feature branch with a clean tree Full branch diff against dev
On dev or master with a clean tree Ask which branch or PR to review

Ask only when the table gives no answer. Status line example: Reviewing branch diff against dev (12 files)…

Step 2 — Collect the diff

Write the diff to a temp file and keep the changed-file list. Reviewers read the file; the diff is never pasted into their prompts. Noise files are excluded from every scope. Set SCOPE to local, branch, pr or paths from Step 1 and run only that branch of the case.

git fetch -q origin dev
EXCLUDE=(':!package-lock.json' ':!**/__screenshots__/**' ':!public/sw.js' ':!src/libs/lucide/lucideIcons.aliases.ts' ':!src/libs/lucide/lucideIcons.nodes.ts' ':!src/libs/lucide/lucideIcons.tags.ts')
OUT="${TMPDIR:-/tmp}/pubky-review-$(date +%s).diff"

case "$SCOPE" in
  local)   # tracked changes (staged + unstaged) plus untracked files
    git diff HEAD -- . "${EXCLUDE[@]}" > "$OUT"
    git ls-files --others --exclude-standard -- . "${EXCLUDE[@]}" | while read -r f; do git diff --no-index -- /dev/null "$f" >> "$OUT" || true; done   # --no-index exits 1 on a diff
    git status --porcelain -- . "${EXCLUDE[@]}"                       # changed-file list (?? = untracked)
    ;;
  branch)
    RANGE="origin/dev...HEAD"
    git diff "$RANGE" -- . "${EXCLUDE[@]}" > "$OUT"
    git diff --name-status "$RANGE" -- . "${EXCLUDE[@]}"              # changed-file list
    ;;
  pr)      # N = the PR number; works for same-repo and fork PRs
    BASE=$(gh pr view "$N" --json baseRefName --jq .baseRefName 2>/dev/null || echo dev)   # PRs target dev; gh may be absent
    git fetch -q origin "$BASE" "+pull/$N/head:refs/remotes/origin/pr-$N"   # + so a force-pushed PR head still updates
    RANGE="origin/$BASE...origin/pr-$N"
    git diff "$RANGE" -- . "${EXCLUDE[@]}" > "$OUT"
    git diff --name-status "$RANGE" -- . "${EXCLUDE[@]}"              # changed-file list
    ;;
  paths)   # PATHS = the files or directories named by the user; tracked changes plus untracked files under them
    git diff HEAD -- "${PATHS[@]}" "${EXCLUDE[@]}" > "$OUT"
    git ls-files --others --exclude-standard -- "${PATHS[@]}" "${EXCLUDE[@]}" | while read -r f; do git diff --no-index -- /dev/null "$f" >> "$OUT" || true; done
    git status --porcelain -- "${PATHS[@]}" "${EXCLUDE[@]}"           # changed-file list
    ;;
esac

Read the full file on GitHub · 150 lines

Changes

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.

  1. 12d ago Changed ee1af327a55c
  2. 1mo ago First seen · 150 lines · 56 tokens per session scan A 6d78b1dccc97

Subscribe to this mod's changes

pubky-code-review is a skill published in the GitHub repository pubky/pubky-app (26 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 2,689 once invoked, about $0.0002 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 2026-09-16.

Related

Other skills, from other repositories

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens