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 skills add 0xku/kon --skill reviewgit clone --depth 1 https://github.com/0xku/konWrote 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/0xku/kon/review)<a href="https://agentmods.dev/skills/0xku/kon/review"><img src="https://agentmods.dev/badge/skills/0xku/kon/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/0xku/kon/review"><img src="https://agentmods.dev/badge/skills/0xku/kon/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.00866 |
| Opus 5.5 | $0.00004 | $0.00346 |
| Sonnet 5.5 | $0.00002 | $0.00173 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade A, and why
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 2mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the requested code changes as if you are reviewing another engineer's PR.
User-provided target or constraints (honor these): $ARGUMENTS
Target selection
- If no target is provided, review the current code changes: staged, unstaged, and untracked files.
- If the user provides a base branch, review the changes that would merge into that branch. Find the merge base and inspect the diff from that commit.
- If the user provides a commit SHA, review only the changes introduced by that commit.
- If the user provides a PR number, PR URL, or text like
PR#68 feat/headless-mode "feat: add non-interactive prompt mode", assume the GitHub CLI is available. Usegh pr viewto inspect PR metadata, resolve the base/head branches, fetch as needed, compute the merge base, and review the PR diff. Do not checkout a different branch unless the user explicitly asks or confirms. - For PRs, do not assume the head branch exists on
origin; it may live on a contributor fork. Prefergh pr checkout --detach <number>only if checkout is acceptable, or fetch the head repository/ref reported bygh pr view --json headRepository,headRefNameinto a temporary remote/ref before diffing. - For a PR scenario such as
/review PR#68 feat/headless-mode "feat: add non-interactive prompt mode", use the PR number/title/branch as hints, verify them withgh pr view 68, then review the code changes relative to the PR base branch.
Review rubric
Only report issues the original author would likely fix if they knew about them.
Flag a finding only when:
- it meaningfully affects correctness, security, performance, reliability, or maintainability;
- it is discrete and actionable;
- it appears introduced by the reviewed change;
- you can identify the affected code path or user scenario;
- it is not merely a style preference, nit, or intentional behavior change.
Do not stop at the first issue. Return all qualifying findings. If there are no findings worth fixing, say so clearly.
Investigation guidance
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.
- 2mo ago First seen · 73 lines · 11 tokens per session scan A 91f9fbe761a9
review is a skill published in the GitHub repository 0xku/kon (356 stars, last pushed 26d ago), licensed MIT. It adds 11 tokens to every session and 866 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
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…
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…
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…