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/basementstudio/xmcp/review-rulesgit clone --depth 1 https://github.com/basementstudio/xmcpWrote 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/basementstudio/xmcp/review-rules)<a href="https://agentmods.dev/commands/basementstudio/xmcp/review-rules"><img src="https://agentmods.dev/badge/commands/basementstudio/xmcp/review-rules.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00209 |
| Opus 5 | $0.00005 | $0.00105 |
| Sonnet 5 | $0.00002 | $0.00042 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
review-rules 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 4d 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
Run a rule-by-rule review of the current working tree against the tracked agent guidance and review standards.
Do this:
- Read
AGENTS.md, the applicable scopedAGENTS.mdfiles, andREVIEW_RULES.md. - Gather the diff:
git diff HEADgit diff --cachedgit status --short
- For each relevant standard, produce:
- Rule name:
pass|fail|n/a - If
fail: cite the specificfile:line, quote the offending code, and suggest the concrete fix. - If
n/a: one short sentence on why it does not apply to this diff.
- Rule name:
- End with a Summary listing only failing rules, ordered by severity: structural/design issues first, then mechanical issues.
Do not modify files during the review. Output only.
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.
- 4d ago First seen · 25 lines · 9 tokens per session scan A b6afa3bb6136
review-rules is a command published in the GitHub repository basementstudio/xmcp (1,325 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 209 once invoked, about $0.0000 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
deslop
Remove AI-generated code slop from the current branch's changes.
triage
Triage Linear issue with comprehensive analysis.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
init
Command "init" from ErisPulse/ErisPulse, covering erispulse.cli.commands.init 模块, 模块概述, 函数列表, validateprojectname(name: str) and 类列表.