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/address-reviewgit 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 | $0.00014 | $0.00492 |
| Opus 5 | $0.00007 | $0.00246 |
| Sonnet 5 | $0.00003 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
address-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Address review comments on PR #$ARGUMENTS for cloudflare/vinext.
Step 1: Read all review feedback
gh pr view $ARGUMENTS --comments
gh api repos/cloudflare/vinext/pulls/$ARGUMENTS/reviews
gh api repos/cloudflare/vinext/pulls/$ARGUMENTS/comments
Step 2: Categorize each comment
For every review comment, decide:
- Fix needed: A legitimate issue introduced by this PR. Fix it.
- Out of scope / pre-existing: A real problem, but not introduced by this PR. File a GitHub issue to track it.
- Disagree: The reviewer is wrong or it's a style preference. Reply explaining why.
Step 3: Make fixes
Work in ../vinext-fix-$ARGUMENTS/:
- Address each legitimate comment with a code fix
- Run the full check suite:
pnpm run build pnpm test pnpm run typecheck pnpm run lint - Commit:
fix: address review feedback - Push
Step 4: File follow-up issues
For each out-of-scope finding, create a tracked issue:
gh issue create \
--title "<concise description>" \
--body "Identified during review of #$ARGUMENTS.
## Context
<what was found and why it matters>
## Suggested approach
<if you have one>"
Do NOT skip this. The whole point is to avoid losing track of work.
Step 5: Reply to review comments
For each comment that was addressed, reply confirming the fix:
gh api repos/cloudflare/vinext/pulls/$ARGUMENTS/comments/{comment_id}/replies \
-f body="Fixed in <commit sha>"
For disagreements, reply with your reasoning.
Step 6: Enable auto-merge
gh pr merge $ARGUMENTS --auto --squash --delete-branch
Step 7: Summary
Print a final summary:
- Comments addressed (with commit references)
- Follow-up issues filed (with issue numbers and links)
- Auto-merge status
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.
- 3d ago First seen · 80 lines · 14 tokens per session scan A 47bfa0637bdd
address-review is a command published in the GitHub repository cloudflare/vinext (8,722 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 492 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.