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/stacklok/toolhive/code-review-assistnpx skills add stacklok/toolhive --skill code-review-assistgit clone --depth 1 https://github.com/stacklok/toolhiveWhat 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 | $0.00048 | $0.02843 |
| Opus 5 | $0.00024 | $0.01422 |
| Sonnet 5 | $0.00010 | $0.00569 |
| Haiku 4.5 | $0.00005 | $0.00284 |
Grade A, and why
code-review-assist 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 2d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Augmentation
Purpose
Act as a senior review partner — not a replacement reviewer. Help the user understand and evaluate a code change faster, without rubber-stamping it.
How This Differs from the code-reviewer Agent
The code-reviewer agent runs autonomously and checks for best practices, security patterns, and conventions. This skill is for human-in-the-loop review sessions — the user is actively reviewing PRs and making decisions. Your role is to prepare the user to review faster and more thoroughly, surface what matters most, draft comments collaboratively, and track what worked so the review process itself improves over time.
Session Planning
When invoked without a specific PR, start by scoping the session:
- Discover PRs: Use GitHub to find (a) open PRs requesting the user's review, (b) PRs merged in the last 2 days that the user hasn't reviewed yet (use a longer lookback only if the user requests it), and (c) open PRs the user has previously reviewed that have new pushes or comments since their last review (contributors may push updates without re-requesting review).
- Load only metadata: Fetch PR title, author, description, and files-changed count. Do not load diffs during session planning — you only need high-level information to help the user prioritize.
- Present the list: Show each PR with title, author, and a risk estimate (high/medium/low based on files changed, area of codebase, and change size). Also note any existing review activity — approved reviews, changes-requested, pending reviews from others, or review comments — so the user knows what's already been covered. If any PRs form a stack (one PR's base branch is another PR in the list), group them and note the dependency chain and what each PR in the stack is responsible for.
- Ask the user:
- Which PRs to include — all open, all merged, or a subset?
- Preferred review order — chronological, highest-risk-first, or by author/area?
- Track coverage: At the end of the session, report which PRs were reviewed, skipped, or deferred so nothing falls through the cracks.
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.
- 2d ago First seen · 152 lines · 48 tokens per session scan A c9598a501863
code-review-assist is a skill published in the GitHub repository stacklok/toolhive (2,065 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 2,843 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
testing-mcp-server-security
Testing Model Context Protocol (MCP) servers and the clients that consume them for tool poisoning, prompt injection via tool descriptions/outputs, over-permissioned and local-credential-stealing tools, config/trust bypasses, and unauthenticated RCE during authorized penetration tests of AI agent infrastructure.
mcp-redteam
Security audit of MCP servers. Safe mode (default) = source analysis + read-only probing. Active mode = controlled payload testing.
brin-check
Scan packages, repositories, MCP servers, domains, web pages, and agent skills for security threats using the brin API. Use this skill before installing dependencies, visiting URLs, or integrating external resources.
browser-control
Requires BROWSERAPIKEY in .env.
browser-skill
Imported from OpenClaw migration.
bugcrowd-reporting
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…