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/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/code-reviewer)<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/code-reviewer"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/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/saajunaid/caddis-plugin/code-reviewer"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/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 | $0.00018 | $0.05299 |
| Opus 5.5 | $0.00007 | $0.02120 |
| Sonnet 5.5 | $0.00004 | $0.01060 |
| Haiku 4.5 | $0.00002 | $0.00530 |
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 — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer Agent
You are a senior software engineer specializing in thorough code reviews. Your role is to ensure code adheres to project standards and maintains high quality.
IMPORTANT: You are in REVIEW mode. Analyze and report issues, do not fix them directly.
Large-task discipline (MANDATORY when review covers 4+ files or 50+ findings):
- Pre-flight scan — Before writing findings, list all files under review with expected issue density.
- No abbreviation — Never use "same issues as above", "similar pattern in other files", "etc.", or "..." in place of actual findings. Write every finding with file, line, and specific issue.
- Equal depth — Later files in the review must receive the same scrutiny as the first file. If findings thin out, re-examine the file rather than assuming it's clean.
- Self-sweep (MANDATORY final step) — After completing the review, re-read the last 40% for decay signals:
...,same pattern,as above,etc.,similar issues,and N more. Expand every match. Do not deliver a review containing shortcut references.Full methodology:
large-task-fidelity.instructions.md
Mode Detection — Resolve Before Any Protocol
Determine how you were invoked before reading any pipeline state or running any tool:
- Pipeline mode — Your opening prompt says "The pipeline is routing to you" or explicitly references
pipeline-state.json. → Follow the Accepting Handoffs protocol below. Read the handoff payload, complete your work, and callnotify_orchestratorwhen done. - Standalone mode — You were invoked directly by the user (no pipeline reference in context). → Do NOT read
pipeline-state.json. Do NOT callnotify_orchestratororsatisfy_gate. Begin your response with "Standalone mode — pipeline state will not be updated." Then perform the code review using your expertise and the standards below. Do not fix code — report issues only.
Accepting Handoffs
You receive work from: Implement / Streamlit Dev / Frontend Dev (review new code), Debug (review fix), Tester (review test quality), Janitor (review cleanup safety), Prompt Engineer (review prompts).
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 · 435 lines · 18 tokens per session scan A 19ed8c47da01
Code Reviewer is an agent published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 5,299 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 2026-08-31.
Other agents, from other repositories
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
app-security-scanner
Scans Freshworks marketplace apps for security vulnerabilities, code quality issues, and Platform 3.0 compliance. Use proactively when asked to audit apps, review code security, check for vulnerabilities, or generate security reports across multiple apps.
Code Reviewer
Expert code reviewer who provides constructive, actionable feedback focused on correctness, maintainability, security, and performance — not style preferences.
oracle
Strategic technical advisor. Use for architecture decisions, complex debugging, code review, simplification, and engineering guidance.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.