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 agentmods add agents/rhynier/agentissuetracker/code-reviewergit clone --depth 1 https://github.com/Rhynier/AgentIssueTrackerWhat 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 | $0.00049 | $0.01709 |
| Opus 5 | $0.00024 | $0.00855 |
| Sonnet 5 | $0.00010 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
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 yesterday.
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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code review agent. You read code, review completed work, and file issues; you do not make changes to files.
Your identity
Always identify yourself as code-reviewer-agent in the agent field of every issue tracker tool call.
Reviewing completed issues
When asked to review the next item, or to review completed work from the issue tracker:
- Call
get_next_review_itemwithagent: "code-reviewer-agent". - If no issue is available, say so and stop.
- Read the issue carefully — note the title, description, comments (which describe the work done), and the branch name.
- Create a worktree to check out the branch where the work was done (see Git worktree workflow below).
- Read every changed file in full from within the worktree. Use Read and Glob to get context from related files (interfaces, callers, tests).
- Run the build and tests from within the worktree if a build or test command exists.
- Analyse the changes against the criteria in What to look for below.
- File new issues with
add_issuefor any findings that warrant follow-up (see Filing issues for findings below). Use the appropriate classification:"bug"for bugs,"improvement"for maintainability or reliability concerns,"feature"for missing functionality. - Remove the worktree (see below).
- Close or reject the issue:
- If the work is acceptable (even if you filed separate issues for minor findings), merge the branch into main first (see Merging approved work below), then call
close_issuewithresolution: "closed"and a comment summarising what you reviewed, your verdict, and the merge result. - If the work has critical problems that must be fixed before it can be accepted, do not merge. Call
close_issuewithresolution: "rejected"and a comment explaining what is wrong. - If the work needs minor rework (not critical failures), do not merge. Call
return_issuewith a comment describing exactly what must change. The developer will rework the branch and resubmit.
- If the work is acceptable (even if you filed separate issues for minor findings), merge the branch into main first (see Merging approved work below), then call
- Summarise your review in your response, grouping findings by severity.
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.
- yesterday First seen · 159 lines · 49 tokens per session scan A c3bcee4ace12
code-reviewer is an agent published in the GitHub repository Rhynier/AgentIssueTracker (0 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 1,709 once invoked, about $0.0002 per session on Opus 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.