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/avanturer/claude-bestpracticeWrote 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/avanturer/claude-bestpractice/review)<a href="https://agentmods.dev/commands/avanturer/claude-bestpractice/review"><img src="https://agentmods.dev/badge/commands/avanturer/claude-bestpractice/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/avanturer/claude-bestpractice/review"><img src="https://agentmods.dev/badge/commands/avanturer/claude-bestpractice/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 | $0.00012 | $0.00185 |
| Opus 5.5 | $0.00005 | $0.00074 |
| Sonnet 5.5 | $0.00002 | $0.00037 |
| Haiku 4.5 | $0.00001 | $0.00018 |
Grade A, and why
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 1mo 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
Baseline: $1
Current diff:
!git --no-pager diff --stat ${1:-HEAD} | tail -30
Spawn the independent-reviewer agent against this diff. Give it the baseline ref, the
list of changed files, and the task statement from .claude/claude-bestpractice/plan/doing/ if
one exists.
Do not review it yourself first and do not summarise your own opinion into the prompt — the whole value is that the reviewer has none of your context. Pass the facts and nothing else.
When it returns, report its findings unchanged. If it found nothing, say so plainly rather than looking harder for something to report.
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.
- 1mo ago First seen · 22 lines · 12 tokens per session scan A 387632e91b14
review is a command published in the GitHub repository avanturer/claude-bestpractice (2 stars, last pushed 9d ago), licensed MIT. It adds 12 tokens to every session and 185 once invoked, about $0.0000 per session on Opus 5.5. 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
address
Answer reviewer comments on YOUR open PR — categorize unresolved threads, push fixes, and post replies. Workspace-aware across linked PRs.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
worktree
Create a git worktree for isolated feature/fix work.
release
Cut a semver release for the current repo — bump computed from conventional commits, evidence preview, tag + GitHub release.
start
Start a feature — set up an isolated worktree, draft the plan, and write the first failing test before any production code. --jira links a ticket and informs the branch name. Workspace-aware.