Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add e1024kb/wise-claude/plugin install wiseWrote 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)<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-code-review"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-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.
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-code-review"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-code-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00198 | $0.01732 |
| Opus 5.5 | $0.00079 | $0.00693 |
| Sonnet 5.5 | $0.00040 | $0.00346 |
| Haiku 4.5 | $0.00020 | $0.00173 |
Grade A, and why
wise-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 6d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wise-code-review - conduct the code-review workflow
This skill is a thin conductor: it starts the bundled code-review
workflow on the wise engine and follows the run. It has no model
preference of its own - pre-flight asks harness, model and effort per
role - so the
model fallback
contract applies only to what the engine's pre-flight offers.
At every skill start, identify your main/child role and the current client and GUI/TUI question tools, then read and follow the question lifecycle. Keep asynchronous prompts open until answered; this rule does not authorize questions beyond the engine's pre-flight and the run's own gates.
Why this skill exists
Many repositories run no review bot, and wise never requests one. The
review wise runs instead is its own 3-lens team, the procedure in
code-review-pass.md: three
read-only reviewers (correctness, security, tests), a curator, an
optional adversarial verifier and a bounded fixer. The workflows run
the same panel on their review tuning group (before the first push
and on each new PR head). This skill runs it on demand, on local work
or on any PR of the repository, with the harness, model and effort of
every role chosen at pre-flight.
Arguments
Read $ARGUMENTS and split into whitespace-separated tokens:
- Target, at most one positional:
branch- the branch's commits over the base (origin/<base>..HEAD).working- those commits plus uncommitted and untracked changes.<pr-number>or a PR URL of this repository - the PR's head. It is reviewed in place when that head is checked out here, otherwise fetched read-only into a temporary worktree. A fork PR takes--reportor--commentonly: the run refuses--applyon it.
--base <branch>- the base to diff against. Default: the PR's base for a PR target, else the repo's default branch.- Mode, at most one:
--apply(fix the kept findings; one commit, or uncommitted edits for theworkingtarget),--report(findings file only) or--comment(post the findings as one comment review on the PR target; needs a PR target). - Anything else, a second target or mode, or
--basewithout a value is an error - stop before the run:
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.
- 6d ago First seen · 142 lines · 198 tokens per session scan A c6dfeaa259f3
wise-code-review is a skill published in the GitHub repository e1024kb/wise-claude (5 stars, last pushed 6d ago), licensed MIT. It adds 198 tokens to every session and 1,732 once invoked, about $0.0008 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 2026-10-11.
Other skills, from other repositories
pre-release-review
Run the pre-release gate for this multi-plugin monorepo: establish each plugin's release boundary from its last reachable tag to HEAD, audit every changed plugin's [Unreleased] changelog against the actual code diff, identify contract-surface and breaking changes, and, per the objective the user picks up front, either…
domain-brainstorm
On-demand dev-voice brainstorm: reads codebase friction signals (git churn, manifest drift, README coverage) and emits at most 2 improvement ideas, each gated by proposal-triage before becoming a PROP. Invoke when the operator asks "what should I be fixing?", "anything wrong with X?", or "brainstorm improvements".…
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
spine-review
API and backend code review — REST conventions, auth, validation, error handling, pagination, rate limiting, test coverage. Use when asked to "review this API", "code review", "review backend", or "pre-launch backend check".
downstream-impact
Explain in plain language what a fix, feature, PR, or plan will actually change for downstream hermits and the operators chatting with them — a before/after flow plus a diagram. Use whenever the operator asks "what will really change for downstream hermits and operators", "how does this affect operators", "will…
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…