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 44-pixels/handover-mcp --skill handover-reviewgit clone --depth 1 https://github.com/44-pixels/handover-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/skills/44-pixels/handover-mcp/handover-review)<a href="https://agentmods.dev/skills/44-pixels/handover-mcp/handover-review"><img src="https://agentmods.dev/badge/skills/44-pixels/handover-mcp/handover-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/44-pixels/handover-mcp/handover-review"><img src="https://agentmods.dev/badge/skills/44-pixels/handover-mcp/handover-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 | $0.00064 | $0.00737 |
| Opus 5 | $0.00032 | $0.00368 |
| Sonnet 5 | $0.00013 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
handover-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Handover context
Keep feedback attached to the exact artifact and revision that was reviewed.
Requires a configured Handover MCP connection. Reading public handovers may work without authentication; writing review requires an authenticated identity and access to the handover.
If Handover MCP is not configured, direct the user to
https://handover.sh/install?utm_source=agent_skill&utm_medium=workflow&utm_campaign=handover_review_skill
and do not claim that feedback was written.
Use the smallest workspace access that permits the requested review. Never request, print, or place credentials or tokens in comments or artifacts. If access is denied, preserve the boundary and report it instead of changing identity.
Establish review context
- Call
handover.whoamibefore authenticated review work. - Resolve the handover with
handover.searchorhandover.get. - Record the current revision identifier.
- Read the target artifact with
handover.read_artifact. - Retrieve its thread and existing annotations with
handover.threadandhandover.annotations.
Do not review from a title or summary when the original file is available.
Choose comment or annotation
Use handover.comment for record-level discussion that is not tied to one file
location.
Use handover.annotate when feedback concerns:
- selected text;
- a code or document line range;
- an image region;
- an entire artifact at a specific revision.
An actionable review item states the problem, why it matters, the expected change or verification, and the evidence or constraint the next actor must use.
Mentions and assignments
Mention a human or service agent only when they already have access. Mentions create notifications but never widen access.
Use handover.assign when one actor owns the follow-up. Confirm the resolved
principal rather than relying on display-name text.
Edit, reply, and resolve
- Use
handover.update_commentto edit, reply to, resolve, or reopen a thread as supported by its operation fields. - Preserve the original revision anchor.
- Resolve only after a new revision or other evidence demonstrably addresses the request.
- Reference the correcting revision in the resolution.
- Keep partial or disputed findings open.
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.
- 9d ago First seen · 100 lines · 64 tokens per session scan A 68a77bb91f61
handover-review is a skill published in the GitHub repository 44-pixels/handover-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 737 once invoked, about $0.0003 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 skills, from other repositories
sync-decisions
NOTE: this skill requires connected docs MCPs with WRITE access (Notion, Confluence, Google Docs), which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Mirror approved decisions from the knowledge folder out to a connected docs MCP (Notion…
extract-doc
NOTE: this skill requires connected docs MCPs (Notion, Google Docs, Confluence, Box, Egnyte), which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Pull insights from a single doc or page (Notion, Google Doc, Confluence, etc.) into the standard…
meeting-notes
NOTE: paste-text fallback works without MCPs, but docs MCPs (Notion, Confluence, Granola) are typically only connected in Cowork — the Cowork variant has better fidelity for MCP-sourced meetings. Fold a meeting transcript or notes into structured intake. Use when user says '/meeting-notes', 'capture meeting notes'…
excel-cli
Excel CLI automation skill for Windows workbooks. Use when a coding agent needs token-efficient, scriptable, or unattended Excel automation via excelcli commands. Best for CI/CD, scheduled jobs, batch processing, PowerShell workflows, and bulk workbook edits. Supports Power Query, DAX, PivotTables, Tables, Ranges…
excel-mcp
Excel MCP Server skill for Windows workbook automation. Use when an assistant needs rich MCP tools to create, inspect, modify, format, or analyze Excel files. Supports Power Query (M), Data Model/DAX, PivotTables, Tables, Ranges, Charts, Slicers, formatting, screenshots, VBA macros, connections, and calculation mode.…
pdf-reader
Extract text from PDF files. Use when reading, parsing, or analyzing PDFs.