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 commands/cloudflare/vinext/review-prgit clone --depth 1 https://github.com/cloudflare/vinextWhat 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 | $0.00011 | $0.00383 |
| Opus 5 | $0.00005 | $0.00192 |
| Sonnet 5 | $0.00002 | $0.00077 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
review-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Review pull request #$ARGUMENTS on cloudflare/vinext.
Steps
-
Read context: Run
gh pr view $ARGUMENTSto understand the PR — what issue it fixes, what the author claims it does. -
Read the diff: Run
gh pr diff $ARGUMENTSto see every change. -
Read full files: For each modified file, read the complete file (not just the diff) so you understand the surrounding code and can catch issues the diff alone won't reveal.
-
Check server parity: If any of these files were touched, check whether the others need matching changes:
packages/vinext/src/entries/app-rsc-entry.tspackages/vinext/src/server/dev-server.tspackages/vinext/src/server/prod-server.tspackages/vinext/src/cloudflare/worker-entry.ts
-
Check test coverage: Are the changes tested? Are edge cases covered? Run
gh pr diff $ARGUMENTSagain filtered to test files if needed. -
Post review: Use
gh pr review $ARGUMENTSwith your assessment:--approveif the PR is clean--request-changes --body "..."if there are blocking issues--comment --body "..."if there are only suggestions
For inline comments on specific files/lines, use:
gh api repos/cloudflare/vinext/pulls/$ARGUMENTS/comments -f body="..." -f path="..." -F line=N -f side="RIGHT"
Be thorough. This is the only review gate before merge.
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.
- 2d ago First seen · 36 lines · 11 tokens per session scan A a593319789f4
review-pr is a command published in the GitHub repository cloudflare/vinext (8,722 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 383 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.