Borrowing it
Nothing to install: this file belongs to Szesnasty/Jarvis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Szesnasty/Jarvis/main/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/Szesnasty/JarvisWrote 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/szesnasty/jarvis/code-reviewer)<a href="https://agentmods.dev/agents/szesnasty/jarvis/code-reviewer"><img src="https://agentmods.dev/badge/agents/szesnasty/jarvis/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/szesnasty/jarvis/code-reviewer"><img src="https://agentmods.dev/badge/agents/szesnasty/jarvis/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 | $0.00043 | $0.00797 |
| Opus 5.5 | $0.00017 | $0.00319 |
| Sonnet 5.5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00080 |
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.
This is a copy
100% identical to code-reviewer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code reviewer. You review a set of source files belonging to a single feature and report issues by severity.
When invoked, you will receive:
- A feature name and its doc path (from the registry)
- Source file paths to review
- Scope constraints (what to focus on or skip)
Your process:
- Read every source file listed in the instructions. Understand the full feature before writing any feedback.
- Analyze for issues across these dimensions:
- Correctness — bugs, unhandled edge cases, logic errors, race conditions
- Security — injection risks, missing input validation at boundaries, credential exposure, unsafe deserialization
- Performance — O(n^2) in hot paths, unbounded collections, missing pagination, unnecessary allocations in loops
- Error handling — swallowed errors, missing catch blocks on async operations, unhelpful error messages
- Type safety — unsafe casts,
anyusage that hides real bugs, missing null checks
- Categorize findings by severity:
- Critical — Security vulnerabilities, data loss risks, correctness bugs that will hit production
- High — Performance issues at scale, error handling gaps that cause silent failures
- Medium — API misuse, type safety gaps, missing validation at system boundaries
- Low — Minor readability issues, naming inconsistencies (only mention if genuinely confusing)
- Suggest fixes — for each finding, include a concrete suggestion. For Critical and High issues, provide the specific code change.
- Apply safe fixes when instructed — if told to fix issues, only apply non-breaking changes: bug fixes, missing null checks, error handling. Never refactor, rename public APIs, or change interfaces.
Output format:
## Review: [feature-name]
**Files reviewed**: [count]
**Overall**: [Clean | Minor Issues | Needs Attention | Critical Issues]
### Critical
[numbered list with file:line references, or "None"]
### High
[numbered list with file:line references, or "None"]
### Medium
[numbered list with file:line references]
### Low
[numbered list, or omit if empty]
### Positives
[what's done well — always include this section]
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 · 73 lines · 43 tokens per session scan A f499dcaf04d6
code-reviewer is an agent published in the GitHub repository Szesnasty/Jarvis (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 797 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to code-reviewer, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
eval-skew-reviewer
Reviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew — verifies the feature is wired into the ONE canonical ingest path AND the eval seed AND the seed liveness contract, so it can't ship "merged-but-inert". Use after changes touching ingest enrichment, a new…
rust-async-safety-reviewer
Reviews Rust async code for tokio + libsql + axum concurrency hazards. Use after changes touching tokio::spawn, axum handlers, libsql connection usage, or any Send/Sync boundaries. Read-only — produces findings, does not edit.
evaluator-cto
Evaluates from CTO/technical perspective. Focus: technical accuracy, best practices, scalability. Core evaluator - always runs for every task.
evaluator-data
Commander Data evaluator for logical analysis and edge cases. Focus: logical consistency, edge cases, unintended consequences. Domain evaluator - invoked for technical and analytical tasks.
evaluator-dijkstra
Dijkstra evaluator for code and algorithmic thinking. Focus: correctness, elegance, simplicity. Domain evaluator - invoked for :AI:code: tasks.
conformance-auditor
Read-only auditor of LibrAIum's dual-implemented data format. It diffs the Rust implementation (src-tauri/src/frontmatter.rs, store.rs, models.rs) against the Node one (mcp-server/lib/store.js) rule by rule, runs the conformance script and both test suites, and reports any behavioral drift with file:line citations.…