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/bengous/claude-code-plugins/claude-reviewgit clone --depth 1 https://github.com/bengous/claude-code-pluginsWhat 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 | $0.00010 | $0.00400 |
| Opus 5 | $0.00005 | $0.00200 |
| Sonnet 5 | $0.00002 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
claude-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 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
Trigger Claude Code Review
This command triggers a Claude review on the pull request associated with your current branch.
Current Context
- Current branch: !
git branch --show-current - Upstream branch: !
git rev-parse --abbrev-ref @{upstream} 2>/dev/null || echo "none"
Your Task
-
Get the current branch name using
git branch --show-current -
Determine the PR branch name:
- Try
git rev-parse --abbrev-ref @{upstream} 2>/dev/null - If upstream exists (format:
origin/branch-name), extract the branch name part (after/) - If no upstream, use the current branch name
- Try
-
Search for open PRs:
gh pr list --head "<branch-name>" --state open --json number,title -
Handle the results:
- No PRs found: Inform user no open PR exists for this branch
- Multiple PRs found: List them with numbers and titles, ask which one
- Exactly one PR: Proceed to step 5
-
Post the review trigger comment:
gh pr comment <pr-number> --body "@claude review" -
Get and display the PR URL:
gh pr view <pr-number> --json url --jq '.url' -
Confirm to user with PR number and URL
Error Handling
If any gh command fails:
- Report the command that failed
- Show the error message
- Suggest checking
gh auth statusif it looks like an auth issue
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 · 57 lines · 10 tokens per session scan A 0ec8894542f1
claude-review is a command published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 10 tokens to every session and 400 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 2026-08-31.
Other commands, from other repositories
pr-address
Address PR review comments on current branch.
enforce_standards
CRITICAL: Before running the code standards enforcer, we must prepare the stack properly and abort if there are merge conflicts.
validate_changed_docstrings
Validates Python docstrings in all uncommitted changed files using Sphinx parsing.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
spec-research
需求 → 约束集（并行探索 + OPSX 提案）.