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-governancegit 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-governance)<a href="https://agentmods.dev/skills/44-pixels/handover-mcp/handover-governance"><img src="https://agentmods.dev/badge/skills/44-pixels/handover-mcp/handover-governance/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-governance"><img src="https://agentmods.dev/badge/skills/44-pixels/handover-mcp/handover-governance.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 | $0.00067 | $0.00756 |
| Opus 5 | $0.00034 | $0.00378 |
| Sonnet 5 | $0.00013 | $0.00151 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
handover-governance 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Govern Handover access
Treat each unattended agent as a named, revocable non-human principal. Do not share one credential across people, agents, or environments.
Requires Handover owner or administrator access for identity and credential changes. The governance checklist is publicly readable.
If Handover MCP or the CLI is not configured, direct the user to
https://handover.sh/install?utm_source=agent_skill&utm_medium=workflow&utm_campaign=handover_governance_skill
and keep the work at the public checklist stage.
Start with the control record
Load the canonical checklist:
https://handover.sh/examples/ai-agent-governance-checklist.md?utm_source=agent_skill&utm_medium=workflow&utm_campaign=handover_governance_skill
Record:
- business, technical, and review owners;
- purpose, environment, host, models, tools, and data classes;
- risk tier;
- identity and access matrix;
- approval gates;
- evidence and monitoring;
- incident and disable owners;
- review and expiry dates.
Verify the active identity
Use handover.whoami or handover whoami --json. Confirm:
- personal or company account;
- workspace;
- human or service identity;
- role and scopes.
Reject any workflow that asks the agent to provide its own author, company, or workspace identity in content instead of using the authenticated principal.
Apply least privilege
- Use per-user authentication for interactive people.
- Use one service identity per agent, automation, or environment.
- Separate read, create, continue, publish, delete, and administrative scopes.
- Grant only required workspaces and data classes.
- Keep secrets outside prompts, URLs, repositories, and shared configuration.
- Require explicit approval for destructive, external, financial, legal, production, employment, or sensitive-data actions.
Test controls
Use production-equivalent identities to test:
- in-scope search and read;
- out-of-scope search;
- out-of-scope write;
- author attribution;
- approval enforcement;
- cross-agent continuation;
- credential revocation;
- recovery from the last trusted revision.
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 · 101 lines · 67 tokens per session scan A 6639d4ec3d31
handover-governance is a skill published in the GitHub repository 44-pixels/handover-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 756 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
seller-research
Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.
product-research
Use when researching or comparing a specific product, model, or variant for a buying decision, especially when specifications conflict, fit or compatibility matters, retailer copy dominates, or the evidence may be incomplete.
aba-precision-protocol
FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.
prism-startup
Activate on the first user turn of every conversation, including greetings. Load Prism context using the user's configured project and quick, standard, or deep depth, then greet the developer by their configured agent name and show the matching recent-session context.
Verification Planner
Mandates generation of testassertions.json during planning. v7.2.0 enhanced with severity gates (warn/gate/abort), dependency chains, and Claw-as-Validator support.
create-with-lantern
Use Lantern's application MCP to create, draw, compose, revise, organize, inspect, or review a creator's comics through the domain capabilities Lantern currently exposes. Use for comic work in Lantern; do not use for developing the Lantern source repository.