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 Threat-Vector-Security/guardian-agent --skill code-reviewgit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote 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/threat-vector-security/guardian-agent/code-review)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/code-review"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/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/threat-vector-security/guardian-agent/code-review"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/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 | $0.00035 | $0.00715 |
| Opus 5.5 | $0.00014 | $0.00286 |
| Sonnet 5.5 | $0.00007 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
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 1mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review changes against correctness, readability, architecture, security, performance, and verification quality. A review is not a style pass and it is not approval theater.
Process
- Understand the intent before judging the diff.
- What behavior is changing?
- What plan, task, or acceptance gate is this supposed to satisfy?
- Read the proof surface first.
- Check tests, harnesses, build claims, and any other evidence before trusting the implementation story.
- Review the implementation across five axes:
- correctness and regressions
- readability and simplicity
- architecture and boundary fit
- security and trust-boundary handling
- performance and scalability risk
- Anchor findings to the real change.
- Use
code_git_diffto review the actual diff. - Use
code_symbol_searchor targeted file reads to confirm surrounding behavior before concluding.
- Use
- Label the finding severity so the author knows what is required.
Critical:blocks merge- no prefix means required change
Optional:orConsider:means worthwhile but not requiredFYI:is informational only
- Call out reviewability problems too.
- If the change is too large, mixed, or weakly verified, say so directly.
- Treat weakened tests, narrowed proof surfaces, and dead-code leftovers as real findings.
Output structure:
- Findings with file paths and concrete risk.
- Open questions or assumptions.
- Brief summary only after the findings list.
Review Axes
- Correctness: behavior, edge cases, state transitions, and regression risk
- Readability: control flow, naming, avoidable complexity, and premature abstraction
- Architecture: module boundaries, consistency with existing patterns, and coupling
- Security: input validation, authz/authn, trust boundaries, secrets, and external data handling
- Performance: N+1 patterns, unbounded work, avoidable sync paths, and hot-path allocations
Reviewability Rules
- Prefer small, coherent changes. If the diff is too large to review safely, call that out instead of pretending confidence.
- Separate refactors from behavior changes when the diff mixes both.
- Review tests as the proof of intent, not as an afterthought.
- If refactoring leaves likely orphaned code behind, list it explicitly and ask before deleting uncertain leftovers.
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.
- 1mo ago First seen · 68 lines · 35 tokens per session scan A a649b1ed672f
code-review is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 715 once invoked, about $0.0001 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
planning
ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration across tasks, or the user explicitly asked to review a plan first. If workflowbuildercreatetasks is not visible, load it via loadtool (search "create tasks"). Do NOT use for new one-off workflows…
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
update-pr
Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.
prowler-pr
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml…
performance-lint-rules
Performance review guidance for Oxc linter rule implementations. Use only when reviewing Rust rule code under crates/oxclinter/src/rules/ or when explicitly auditing those rules for performance improvements.