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/rianvdm/product-ai-publicWrote 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/commands/rianvdm/product-ai-public/code-review)<a href="https://agentmods.dev/commands/rianvdm/product-ai-public/code-review"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/code-review/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/commands/rianvdm/product-ai-public/code-review"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/code-review.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 | $0.00009 | $0.00430 |
| Opus 5 | $0.00005 | $0.00215 |
| Sonnet 5 | $0.00002 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
code-review 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.
What it actually says
Review uncommitted changes by default. If no uncommitted changes, review the last commit. If the user provides a PR/MR number or link, fetch it with CLI tools first.
Guidance: $ARGUMENTS
Launch FOUR (4) @code-review subagents in parallel. Give each a different focus area. If the user guidance specifies areas, use those (still include the Codex reviewer). Otherwise default to: (1) correctness, (2) security & resilience, (3) complexity & maintainability, (4) Codex compliance. Include the focus area in each subagent's prompt.
For the Codex reviewer (#4): instruct it to load the codex skill, identify the language(s) in the diff, read the relevant Codex reference files (e.g., references/typescript/README.md for TypeScript), and check the code against each applicable rule. For each violation, cite the specific Codex rule and reference path. Classify findings as either "deviation from Codex" (the code violates a rule) or "codebase-wide gap" (the entire codebase deviates, not just this change). Only flag deviations introduced by this change as actionable; codebase-wide gaps are informational only.
After all four complete, deduplicate their findings — keep the version with better evidence, use the higher severity when they disagree, and drop anything without a file:line reference. Run the project's lint/test commands to catch anything the reviewers missed.
Then launch ONE (1) final @code-review subagent to validate. Pass it the compiled findings, the user guidance, and this instruction: "For each finding, read the code at the referenced file:line. Classify as Confirmed (provably real), Disputed (not supported by the code), or Acknowledged (real but not worth fixing). Return only Confirmed findings."
Present only Confirmed findings to the user, ranked by severity. If nothing survived validation, say so.
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 · 19 lines · 9 tokens per session scan A fade9beb079c
code-review is a command published in the GitHub repository rianvdm/product-ai-public (15 stars, last pushed 2d ago), licensed MIT. It adds 9 tokens to every session and 430 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.