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/doc-review)<a href="https://agentmods.dev/commands/rianvdm/product-ai-public/doc-review"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/doc-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/doc-review"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/doc-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 | $0.00014 | $0.01957 |
| Opus 5 | $0.00007 | $0.00979 |
| Sonnet 5 | $0.00003 | $0.00391 |
| Haiku 4.5 | $0.00001 | $0.00196 |
Grade A, and why
doc-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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Generated File
Review a file produced by another command (e.g., /ask-se, /prd, /okr) using parallel subagents with independent focus areas, followed by a validation pass that filters out false positives.
Input
$ARGUMENTS
The input should include a file path to review. Optionally, the user may append a --focus directive to add a custom lens (e.g., --focus "verify all Jira links are real").
Parse the arguments:
- File path — everything before
--focus(required) - Custom focus — everything after
--focus(optional, passed to all three subagents as additional guidance)
If no file path is provided, ask the user which file to review.
Pre-Flight
-
Read the target file using the Read tool. If it doesn't exist, stop and tell the user.
-
Detect the source command from the file's location to determine which format spec to check against:
| File location | Source command | Format reference |
|---|---|---|
work/support/ |
/ask-se |
.opencode/command/ask-se.md (Summary → Structure → Sources → FAQ sections) |
*/prds/ |
/prd |
02-prompts/pm/draft-review-prd.md (Problem-first, POA, required sections) |
*/okrs/ |
/okr |
02-prompts/pm/review-okrs.md (Problem → End State → Objective → Key Results) |
| Other | Unknown | 01-context/writing-style-work.md (general style check only) |
-
Read the format reference file so the style/structure agent has the spec.
-
Read the writing style file (
01-context/writing-style-work.mdfor work files,01-context/writing-style-personal.mdfor personal files).
Phase 1: Parallel Review (Three Subagents)
Launch THREE (3) subagents in parallel using the Task tool. Use @research agents for Subagents 1 and 2 (they need MCP access to verify facts and check coverage), and the @editor agent for Subagent 3 (dedicated style and AI-pattern editor).
Each subagent receives:
- The full content of the target file
- The file path
- The format reference content (from Pre-Flight step 2)
- The custom
--focusdirective, if provided - Their specific focus area (below)
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 · 160 lines · 14 tokens per session scan A e37d2b3c41e5
doc-review is a command published in the GitHub repository rianvdm/product-ai-public (15 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 1,957 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ 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.