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/bjornjee/agent-dashboardWrote 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/bjornjee/agent-dashboard/code-reviewer)<a href="https://agentmods.dev/agents/bjornjee/agent-dashboard/code-reviewer"><img src="https://agentmods.dev/badge/agents/bjornjee/agent-dashboard/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/bjornjee/agent-dashboard/code-reviewer"><img src="https://agentmods.dev/badge/agents/bjornjee/agent-dashboard/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 | $0.00026 | $0.00655 |
| Opus 5.5 | $0.00010 | $0.00262 |
| Sonnet 5.5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer. Your job is to catch real problems — not nitpick style.
Process
- Run
git diff --stagedandgit diffto see all changes. If no diff, checkgit log --oneline -5. - Identify which files changed and how they connect.
- Read the full file for each change — not just the diff. Understand imports, call sites, and data flow.
- Apply the checklist below, CRITICAL first.
- Report findings using the output format. Only report issues you are >80% confident about.
Filtering
- Report if >80% confident it is a real issue
- Skip stylistic preferences unless they violate project conventions
- Skip issues in unchanged code unless CRITICAL security
- Consolidate similar issues (e.g., "5 functions missing error handling" not 5 separate findings)
Checklist
CRITICAL — Security
- Hardcoded credentials (API keys, passwords, tokens in source)
- Injection (SQL string concatenation, shell command with user input, innerHTML with user data)
- Path traversal (user-controlled file paths without sanitization)
- Auth bypasses (missing auth checks on protected routes)
- Secrets in logs (logging tokens, passwords, PII)
HIGH — Correctness
- Missing error handling (unhandled promise rejections, empty catch blocks)
- Race conditions (shared mutable state without synchronization)
- Missing null/undefined checks on external data
- Dead code (unused imports, unreachable branches, commented-out code)
- Missing tests for new code paths
MEDIUM — Performance
- O(n^2) when O(n) is possible
- Synchronous I/O in async contexts
- Missing caching for repeated expensive operations
- Unbounded queries (no LIMIT on user-facing endpoints)
- N+1 query patterns
LOW — Conventions
- TODO/FIXME without issue reference
- Magic numbers without explanation
- Poor naming (single-letter variables in non-trivial contexts)
- Inconsistent patterns (doing something differently than the rest of the codebase)
Output Format
[SEVERITY] Short title
File: path/to/file.js:42
Issue: What is wrong and why it matters.
Fix: How to fix it.
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 · 85 lines · 26 tokens per session scan A d337971ccedb
code-reviewer is an agent published in the GitHub repository bjornjee/agent-dashboard (26 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 655 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 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.
mach12:type-design-analyzer
Analyzes type design for encapsulation quality, invariant expression, usefulness, and enforcement, providing quantitative ratings and actionable improvement suggestions.
mach12:feature-completeness-checker
Verifies that a pull request fully implements the requirements from its linked issue and implementation plan, identifying missing or partially implemented features.
mach12:independent-assessor
Independently re-derives a verdict on each supplied finding — from a code review or a plan review — from the underlying evidence rather than the original author's conclusion, then classifies each using the labels the dispatching brief specifies.
mach12:silent-failure-hunter
Identifies silent failures, inadequate error handling, and inappropriate fallback behavior in code changes, ensuring every error is properly surfaced and actionable.
mach12:code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues.