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/sebaboler/vanguard/code-reviewnpx skills add SebaBoler/vanguard --skill code-reviewgit clone --depth 1 https://github.com/SebaBoler/vanguardWhat 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 | $0.00042 | $0.00321 |
| Opus 5 | $0.00021 | $0.00161 |
| Sonnet 5 | $0.00008 | $0.00064 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
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 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.
What it actually says
Code Review
Review the change as an independent reviewer who did not write it. Read the diff and the surrounding code, then judge it adversarially.
What to check
- Correctness: logic errors, off-by-one, wrong conditionals, unhandled
null/undefined, broken control flow, race conditions. Trace the actual execution, don't skim. - Error handling at real boundaries: I/O, subprocess, network, parsing. No silent failures, no swallowed errors, no fallback that hides a real problem.
- Security: injection, path traversal, leaked secrets, unsafe input reaching a shell/filesystem.
- Tests: does new behavior have a test? Are edge cases and failure paths covered? Run the project's tests/typecheck if you can.
- Conventions: match the surrounding code's style, naming, and patterns. No new dependency or abstraction that the codebase already provides.
How to report and act
Only act on issues you are confident are real — skip speculative nitpicks. For each real issue, fix it directly in the repo (this is a working review, not a comment-only pass). State what you changed and why. If something is a genuine design concern beyond this change, note it rather than forcing a fix.
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 · 28 lines · 42 tokens per session scan A 11ee70521ad1
code-review is a skill published in the GitHub repository SebaBoler/vanguard (4 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 321 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 2026-08-31.
Other skills, from other repositories
agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).
understand-codebase
Understand an unfamiliar codebase or plan a change safely, using Spine's deterministic knowledge-graph MCP tools. Reach for this before answering structural questions about a repo you don't know, before editing code, or when debugging — it hands you engineering decisions (what a change breaks, what's untested, where a…
autobeat
Use when delegating work to background agents, creating workflows, choosing between autobeat primitives (tasks, pipelines, loops, orchestrations, schedules), monitoring progress, or troubleshooting failures.
source-evaluation
Framework for evaluating source credibility and reliability. Use when assessing whether to trust information.
code-review
Code review checklist and best practices. Use when reviewing code or preparing code for review.
git-workflow
Branch naming, commit message format, and PR conventions. Use when making git commits or creating PRs.