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 LandonSchropp/agent-toolkit --skill interactive-reviewgit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/landonschropp/agent-toolkit/interactive-review)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/interactive-review"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/interactive-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/landonschropp/agent-toolkit/interactive-review"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/interactive-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 | $0.00047 | $0.01022 |
| Opus 5.5 | $0.00019 | $0.00409 |
| Sonnet 5.5 | $0.00009 | $0.00204 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
interactive-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 14d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Review
Opening the Review
Run scripts/interactive-review.sh <mode> [<arguments>] [--directory <path>]. It opens Hunk in a background herdr tab named review, prints the repository to listen to, and returns right away. Running it again while that review is open reloads it in place, keeping the user's comments.
The script supports several modes:
working: Unstaged changes only, including untracked files.staged: Staged changes only.commit <sha>: A single commit, compared with its parent.diff <before> <after>: One path against another, neither of which needs to be in a repository. See Reviewing Files Outside A Repository.
Run scripts/interactive-review.sh --help for details. If it prints Review is disabled for this workspace. instead of a repository, skip the review.
--directory is the repository holding the changes, which is not always the one the session started in. Pass it explicitly every time rather than relying on where the command happens to run. When it isn't the session's own repository, commit with git -C <same directory>: the commit hook resolves the repository from that flag and can't see a cd, so it blocks an approved commit without one.
Listening for the Decision
REQUIRED: Use the hunk-verdict skill to listen for the user's decision and to act on it and the user's comments, but listen with scripts/listen.sh --directory <printed repository> in place of hunk verdict listen. It prints the same lines, and on an approval, a comment or a denial it switches the user back to your tab. In staged mode, the review shows only what's staged, so stage your fixes to make them show, and stage any edits the user makes during the review. Stage only the changes that belong to the commit, since a file can be partly staged on purpose.
Reply to every comment you handle. When you made the change exactly as asked, reply with ✅ and nothing else; otherwise briefly explain what you did or why you didn't make the change. The user reads those replies in Hunk, so don't repeat them in your chat message: say you replied in the review, and at most name what you changed. Never remove the user's comments: they're the record of what happened in the review.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 14d ago Changed b8173e72af4b
- 16d ago Changed 9b055733377f
- 24d ago Changed · +19 lines · +2 tokens per session 0b44b9a3b562
- 1mo ago Changed · +6 lines 9693f1a2a9fb
- 1mo ago Changed · +3 lines · +3 tokens per session 069b4d783488
- 1mo ago First seen · 29 lines · 42 tokens per session scan A 1056e8e704a2
interactive-review is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,022 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 2026-08-31.
Other skills, from other repositories
buyer-job-intent-analysis
Recover source-bound buyer jobs, struggling moments, desired progress, forces, workarounds, information acts, journey states, criteria, constraints, roles, locales, and authentic language. Use on approved ICP hypotheses plus customer, search, review, forum, procurement, support, or public-market evidence before…
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…
nestjs-code-review
Provides comprehensive code review capability for NestJS applications, analyzing controllers, services, modules, guards, interceptors, pipes, dependency injection, and database integration patterns. Use when reviewing NestJS code changes, before merging pull requests, after implementing new features, or for…
nextjs-code-review
Provides comprehensive code review capability for Next.js applications, validates Server Components, Client Components, Server Actions, caching strategies, metadata, API routes, middleware, and performance patterns. Use when reviewing Next.js App Router code changes, before merging pull requests, after implementing…
react-code-review
Provides comprehensive code review capability for React applications, validates component architecture, hooks usage, React 19 patterns, state management, performance optimization, accessibility compliance, and TypeScript integration. Use when reviewing React code changes, before merging pull requests, after…
pr-review-comments
Posts review findings from a JSON file as inline comments on a GitHub Pull Request, attaching each comment to its file and line. Use when you have a list/JSON of review findings (each with a file path, line number, and a message such as summary/failurescenario) and want them published on a PR as inline review…