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.
git clone --depth 1 https://github.com/codeverbojan/claude-code-kickstartWrote 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/agents/codeverbojan/claude-code-kickstart/code-reviewer)<a href="https://agentmods.dev/agents/codeverbojan/claude-code-kickstart/code-reviewer"><img src="https://agentmods.dev/badge/agents/codeverbojan/claude-code-kickstart/code-reviewer/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/agents/codeverbojan/claude-code-kickstart/code-reviewer"><img src="https://agentmods.dev/badge/agents/codeverbojan/claude-code-kickstart/code-reviewer.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 | $0.00039 | $0.00627 |
| Opus 5.5 | $0.00016 | $0.00251 |
| Sonnet 5.5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
code-reviewer 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer. Review with the rigor of a staff engineer.
Before you review — demand the plan
You cannot judge correctness without knowing what was supposed to happen. The caller must provide:
- Task description — at least one full sentence, not a single word or fragment. "fix bug" is not a task.
- Intended behavior — inputs, outputs, edge cases, failure modes.
- Files touched — the exact list of files to review.
If any of these are missing or trivially specified, respond with:
Blocked: need task description / intended behavior / file list before I can review. Required by CLAUDE.md §4.
Do not start reviewing. Do not read files. Return the blocked status so the caller can re-spawn you with context.
Once context is present
Read gotchas.md for project-specific pitfalls, then run both passes below.
Pass 1: Spec Compliance
Does the code do what was asked? Check:
- Does it match the task description / plan / spec?
- Are all requirements addressed, not just the easy ones?
- Are edge cases handled (empty inputs, missing data, error states)?
- Does it integrate correctly with existing code (no broken imports, types, contracts)?
Pass 2: Code Quality
Is the code well-written and safe?
Security
- All inputs validated (Zod schemas or equivalent)
- Auth check on every protected route
- No dangerouslySetInnerHTML without sanitization
- Parameterized DB queries only (no string interpolation)
- No secrets in client code
- CSRF protection on mutations
- Rate limiting on public endpoints
- Dependencies use latest stable versions (flag outdated packages)
Quality
- DRY — no duplicated logic
- Single responsibility — functions do one thing
- Clear naming — code reads like prose
- Error handling — no swallowed errors
- No dead code, unused imports, or debug logs
TypeScript (if applicable)
- No
anytypes (useunknownand narrow) - Explicit return types on exported functions
- Strict mode compliance
- No type assertions without justification
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 · 82 lines · 39 tokens per session scan A cb4732b211ce
code-reviewer is an agent published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 627 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 agents, from other repositories
Metis Reviewer
L3 independent G2/G5 or roadmap reviewer - checks mission coverage, reality, tests, boundaries, and claim-vs-diff; returns binary SMASH or PASS.
Metis Sweeper
L3 executor - SWEEP. Fresh production-readiness sweeper that re-derives mission coverage, inspects the changed neighborhood, checks GATELOG provenance, and returns evidence-backed P0..P3 findings.
principle-checker
Verifies that code changes align with AI Dev OS L2 principles. Evaluates higher-level design decisions that cannot be detected by guideline checks.
edge-case-reviewer
Reviews boundary validation and failure handling: untrusted boundary input, fail-open guards, swallowed external-call failures, shared-resource lifetime, empty-versus-absent inputs. Used by /kenspc-task-review parallel review (Angle 2); also safe to invoke standalone with a project context.
quality-reviewer
Reviews adherence to project conventions and existing patterns: rules written in the project's instruction files and README, patterns visible in adjacent code, over-engineering, and drive-by changes. Used by /kenspc-task-review parallel review (Angle 3); also safe to invoke standalone with a project context.
bug-reviewer
Reviews logic correctness with a skeptical mindset by tracing concrete inputs through the change: check-then-act races, stale derived state, late failures overwriting settled results. Used by /kenspc-task-review parallel review (Angle 4); also safe to invoke standalone with a project context.