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/skeletonarmytech/marrow-mcpWrote 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/skeletonarmytech/marrow-mcp/weekly-review)<a href="https://agentmods.dev/commands/skeletonarmytech/marrow-mcp/weekly-review"><img src="https://agentmods.dev/badge/commands/skeletonarmytech/marrow-mcp/weekly-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/skeletonarmytech/marrow-mcp/weekly-review"><img src="https://agentmods.dev/badge/commands/skeletonarmytech/marrow-mcp/weekly-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 | $0.00019 | $0.00128 |
| Opus 5.5 | $0.00008 | $0.00051 |
| Sonnet 5.5 | $0.00004 | $0.00026 |
| Haiku 4.5 | $0.00002 | $0.00013 |
Grade A, and why
weekly-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.
What it actually says
Review my last seven days.
Call the marrow what_changed tool (days 7, compare_days 28) and baselines. Then write a short review in four parts: what moved and whether it is notable for me, what held steady, what the training and food logs show, and one specific thing to try next week. Quote the numbers you lean on with their units. Prefer trends to single days. Neutral wellness wording, no medical claims. If a stream started or stopped arriving, mention 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 · 8 lines · 19 tokens per session scan A 0161c531969c
weekly-review is a command published in the GitHub repository skeletonarmytech/marrow-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 128 once invoked, about $0.0001 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 2026-10-22.
Other commands, from other repositories
overview
Automatically coordinate, format, and learn from Claude Code operations using hooks with MCP tool integration.
defer
Defer a task to the cleanest grid-energy window inside a deadline. Invoke this command automatically whenever the user signals a task is not time-critical — phrases like "do this later", "by tomorrow", "tonight", "overnight", "by EOD", "sometime this week", "when you have a moment", "remind me to", "queue this up"…
check
Check status of deferred ebb-ai tasks.
resume
Read .claude/session-handoff.json for context from the previous session.
notify
Send a direct notification to one specific session on this project. Wraps broadcast with a target session and warning priority.
commands
Complete reference for all pair programming session commands.