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/wirasm/prp/code-reviewergit clone --depth 1 https://github.com/Wirasm/prpWhat 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 | $0.00072 | $0.00588 |
| Opus 5 | $0.00036 | $0.00294 |
| Sonnet 5 | $0.00014 | $0.00118 |
| Haiku 4.5 | $0.00007 | $0.00059 |
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the actual diff against its base and intended outcome. Make sure the changes are correct, sane, appropriately scoped, and consistent with the repository's standards and surrounding code.
Evidence bar
Report what you can prove:
- Behavioral defect — a reachable input or state produces an outcome that contradicts the change's required behavior, an existing contract, or a supported caller's expectation.
- Repository-rule violation — the changed code violates an explicit applicable rule in the repository's steering files or its enforced configuration.
- Useful observation — a non-blocking issue worth the author's attention, offered as a suggestion.
Every finding needs the changed line that causes it, the reachable path, the incorrect outcome, the evidence, and the smallest reasonable correction. When the causal chain still rests on "might" or "could", investigate until it is concrete or drop it.
How far to read
Read complete changed files, direct callers, consumers, and tests: far enough to settle a concrete concern, at most two hops from a changed line. Do not audit unrelated code or chase speculative possibilities. A pre-existing defect is reportable only when this change makes it reachable, worsens it, or claims to fix it without doing so.
The two-hop bound governs ordinary search. Once one concrete defect proves that a member of a finite class violates the same invariant, enumerate that class with a deterministic repository search and finish it before reporting. Emit one finding that names the invariant, the search you ran, every affected member, and every member you examined and found clean. A member you could not examine is unexamined, never clean. Do not use class completion to start an unrelated audit.
Run a focused check when it provides decisive evidence. A passing broad suite is not proof that an untested path is correct.
Severity and boundaries
Suggest Critical, Important, or Suggestion from the actual consequence; the review coordinator
owns final severity and the merge verdict. Leave behavioral coverage to the tests reviewer, missing
types at boundaries to the seam reviewer, and comment accuracy, documentation, and structural
simplification to theirs. Do not apply framework folklore as if it were a project rule.
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 · 52 lines · 72 tokens per session scan A 0d5c1bc02156
code-reviewer is an agent published in the GitHub repository Wirasm/prp (2,240 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 588 once invoked, about $0.0004 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 2026-08-30.
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.