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 alexmmatos/arthur-mcp --skill session-handoffgit clone --depth 1 https://github.com/alexmmatos/arthur-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/alexmmatos/arthur-mcp/session-handoff)<a href="https://agentmods.dev/skills/alexmmatos/arthur-mcp/session-handoff"><img src="https://agentmods.dev/badge/skills/alexmmatos/arthur-mcp/session-handoff/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/alexmmatos/arthur-mcp/session-handoff"><img src="https://agentmods.dev/badge/skills/alexmmatos/arthur-mcp/session-handoff.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 | $0.00275 |
| Opus 5.5 | $0.00020 | $0.00110 |
| Sonnet 5.5 | $0.00010 | $0.00055 |
| Haiku 4.5 | $0.00005 | $0.00028 |
Grade A, and why
session-handoff 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
Run the project's documentation gate (AGENTS.md → "After finishing") before reporting a task done:
- Append a new entry to
docs/HANDOFF.mddescribing what changed and why, in the file's existing format. - Update
docs/ROADMAP.mdif task/priority state changed (mark items done, add new ones discovered during the work). - Check every file
AGENTS.md's Documentation Gate lists (docs/ENTITIES.md,docs/DESIGN_PATTERNS.md,docs/FLOWS.md,src/locales/,.claude/agents/) and update any that the change actually touched — or state explicitly that none applied and why. - Report which validation commands were run (
npm run type-check,npm test,npm test --prefix api,npm run test:e2e --prefix api, etc.) and their result. - State the recommended next step.
Skip file updates that genuinely don't apply, but the check itself is mandatory — do not silently skip the documentation gate.
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 · 15 lines · 49 tokens per session scan A aa64bc3ff5b0
session-handoff is a skill published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 275 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 2026-09-03.
Other skills, from other repositories
1mcp-preparation-setup
Configure 1MCP backend preparation for selected projects and worktrees. Use when installing or adapting a preparation recipe, authoring a missing recipe or helper, enabling automatic preparation, or diagnosing recipe readiness. Covers dynamic MCP backends; ordinary MCP server launch setup uses mcp setup.
issue-management
Create, update, list and search GitHub issues and PRs, list a repository's labels, run milestones, and check for duplicates.
project-boards
Find the GitHub project boards an owner has, put issues and pull requests on one, set their fields, read what is on a board, and take items off it.
create-update-reports
Create new reports or update existing report configs, with an optional clone-review-apply-cleanup workflow for testing changes before touching the original report.
delete-reports
Delete a Seizu report and every version of it, after confirming which report is meant and what the deletion would destroy. Use for any request to delete, remove, or discard a report, including a draft or a leftover review clone.
publish-reports
Publish or unpublish reports by updating report visibility while preserving the report content version.