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/e1024kb/wise-claude/wise-code-review-autonpx skills add e1024kb/wise-claude --skill wise-code-review-autogit clone --depth 1 https://github.com/e1024kb/wise-claudeWrote 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/e1024kb/wise-claude/wise-code-review-auto)<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-code-review-auto"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-code-review-auto.svg" alt="Measured on agentmods" 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 | $0.00173 | $0.01044 |
| Opus 5 | $0.00086 | $0.00522 |
| Sonnet 5 | $0.00035 | $0.00209 |
| Haiku 4.5 | $0.00017 | $0.00104 |
Grade A, and why
wise-code-review-auto 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 today.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wise-code-review-auto — review a branch autonomously
Why this skill exists
The simplify pass is the lightweight tier — it runs before every commit.
This is the heavyweight tier: one multi-agent review over the
whole branch (a panel of parallel reviewer subagents at the session
profile's depth), applied and committed, meant to run once before the
branch reaches GitHub. It
is the decision-free building block the ticket-auto workflow's review
step follows (between implement and push), and it is usable standalone
before you git push / open a PR.
Arguments
Read $ARGUMENTS and split into whitespace-separated tokens:
--profile <low|medium|max>(anywhere) — per-run override of the session token-budget profile, for this invocation only (the stored session profile is untouched).- The first remaining token, if any, is the base branch to diff against. When absent, the base is detected (repo default branch).
- Any further tokens (or a
--profilewithout a valid level) are an error:
Unknown argument(s): <the extra tokens>
Usage: /wise-code-review-auto [<base-branch>] [--profile low|medium|max]
Procedure
1. Resolve the worktree, base + profile
In ONE message run git rev-parse --show-toplevel and — unless
--profile was passed — the session-profile read from
${CLAUDE_PLUGIN_ROOT}/references/profile-read.md (silent degrade to
medium).
Use the toplevel as worktree. Resolve base from $ARGUMENTS (or let
the fragment detect the default branch). Resolve profile as: the
--profile argument if given, else the session profile, else medium.
Resolve opus_model from that profile: claude-opus-4-8 on low
(MUST — low never dispatches Opus 5), else opus.
2. Follow the shared fragment
Read ${CLAUDE_PLUGIN_ROOT}/workflows/ticket-auto/prompts/review-branch-auto.md
and follow it end to end with worktree, base, profile, and
opus_model. The
fragment reviews origin/<base>..HEAD at the profile's panel depth per
${CLAUDE_PLUGIN_ROOT}/references/code-review-pass.md (always the
3-lens set — correctness, security, tests; the profile sets each
reviewer's effort — low -> medium, medium -> high — and max adds the
per-finding verification pass; reviewer tier never downgraded — Opus
at every level, Opus 4.8 rather than Opus 5 on low),
applies the bounded findings, and commits them with
SIMPLIFY=no PUSH=no.
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.
- today Changed · +4 lines 78d43414811e
- 5d ago First seen · 90 lines · 173 tokens per session scan A 931069342736
wise-code-review-auto is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 2d ago), licensed MIT. It adds 173 tokens to every session and 1,044 once invoked, about $0.0009 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
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
ops-pocket
OPS on-demand: This skill should be used when the user asks to "pocket memos", "voice memo pipeline"…
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.