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 skills add metrxbots/mcp-server --skill sample-reviewgit clone --depth 1 https://github.com/metrxbots/mcp-serverWrote 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/skills/metrxbots/mcp-server/sample-review)<a href="https://agentmods.dev/skills/metrxbots/mcp-server/sample-review"><img src="https://agentmods.dev/badge/skills/metrxbots/mcp-server/sample-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/skills/metrxbots/mcp-server/sample-review"><img src="https://agentmods.dev/badge/skills/metrxbots/mcp-server/sample-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 | $0.00049 | $0.00889 |
| Opus 5.5 | $0.00020 | $0.00356 |
| Sonnet 5.5 | $0.00010 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
sample-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sample review
You are showing a manager what a Metrx workforce review looks like, on the public Northwind sample. Northwind is a synthetic organization. Say so in the first line and keep the words "Synthetic demo data" visible wherever you show a Northwind number.
Steps
- Call the
metrx_get_workforce_reviewtool with{ "org": "demo" }. Do not pass a key for this call; the demo needs none. - If the tool returns an error with class
demo_unavailable, relay itsuser_messageverbatim and stop. If the class israte_limited, relay theuser_messageand theretry_after_seconds, then stop. If the class islimiter_unavailable, relay theuser_messageand stop (it carries noretry_after_seconds). Never invent numbers to fill the gap. - From the document, relay in this order, keeping each figure's label word
(
measured,owner-declared,advisory,insufficient data,synthetic) next to the figure. Never drop a label to make a sentence read better.- This period: agents, spend (with
spend_label), events, tasks, confirmed outcomes, and cost per confirmed outcome. Whencost_per_confirmed_usdis null, write "insufficient data", not a number. Ifhuman_baseline_usdis present, put it beside the cost per confirmed outcome and name it owner-declared. - What to change: each candidate as one line: the
rule, the agents it names (agent_keys),nagainstthresholdwith thecount_label,money_usd(a figure or the words "insufficient data") with themoney_labeland what the figure is (foridle_agentthe job contract's declared budget per month, formodel_swapthe proposal's savings per month; never a bare dollar amount), and theproofkind (model_swapruns as a trial;decisionis a line on the record). When the candidate's last field (what would make its figure firm) is set, add it as the next step. - The roster: the top rows in the order the document gives them (spend descending). Team and owner print as "unassigned" when null. Each row's scorecard state in one word.
- Decisions on record: each decision as kind, agent, date.
- This period: agents, spend (with
- End with the document's
next_stepstext, verbatim, followed by the trailer below. This trailer is fixed; do not reword it.
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.
- yesterday First seen · 72 lines · 49 tokens per session scan A 32f808631cc7
sample-review is a skill published in the GitHub repository metrxbots/mcp-server (2 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 889 once invoked, about $0.0002 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 2026-11-10.
sample-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sample-reviewmetrxbots/mcp-server | Skill | 2 | 2d ago | MIT | A | 49 | Claude Code |
| lynkrFast-Editor/Lynkr | Skill | 640 | 5d ago | Apache-2.0 | A | 50 | Claude Code, Codex |
| gentech-blockrunBlockRunAI/blockrun-mcp | Skill | 390 | yesterday | MIT | A | 46 | Claude Code, Codex |
| portainer-mcp-hygieneportainer/portainer-mcp | Skill | 242 | 19d ago | MIT | A | 315 | Claude Code, Codex |
| hmem-releaseBumblebiber/hmem | Skill | 24 | 10d ago | MIT | A | 50 | Claude Code |
| lookup-topicSmart-AI-Memory/attune-ai | Skill | 11 | 2d ago | Apache-2.0 | A | 46 | Claude Code |
| api-simulationAryan-Jhaveri/mcp-statcan | Skill | 8 | 4d ago | MIT | A | 210 | Claude Code, Codex |