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-test-continuitygit 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-test-continuity)<a href="https://agentmods.dev/skills/44-pixels/handover-mcp/handover-test-continuity"><img src="https://agentmods.dev/badge/skills/44-pixels/handover-mcp/handover-test-continuity/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-test-continuity"><img src="https://agentmods.dev/badge/skills/44-pixels/handover-mcp/handover-test-continuity.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 | $0.00076 | $0.01702 |
| Opus 5.5 | $0.00030 | $0.00681 |
| Sonnet 5.5 | $0.00015 | $0.00340 |
| Haiku 4.5 | $0.00008 | $0.00170 |
Grade A, and why
handover-test-continuity 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.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Handover continuity
Prove that work survives a change of identity, host, review state, and revision. Do not report a continuity pass merely because the endpoint responded or a create call succeeded.
Distinguish the test layers
Report each layer separately:
- Connectivity: the host can reach Handover and list or call tools.
- Workflow completion: one authenticated actor publishes and reads back an immutable multi-file revision.
- Continuity: another authenticated actor reviews exact evidence, a later revision corrects it, and a fresh successor continues without the original chat.
Use handover-verify instead when the user only needs a read-only connection
or identity check.
Preconditions
Require:
- Principal A with read and write access;
- Principal B with read and annotation access;
- Principal C with read and write access, which may be Principal A;
- Principal D outside the workspace for the denied test;
- a dedicated test workspace or an explicit integration-test label; and
- permission to create harmless test data and revoke a test credential.
Grant each principal only the smallest role and workspace scope required for its checkpoint. The test must not use owner access where a member, reviewer, reader, or denied principal is the behavior under evaluation.
Use a unique marker such as:
e2e-mcp-handoff-YYYYMMDD-HHMMSS
Never request, display, log, or publish credentials. Do not put hidden reasoning or unrelated personal data in artifacts.
If the required identities or permissions are unavailable, run only the provable subset and mark every skipped checkpoint. Do not widen access merely to make a test pass.
1. Verify the publisher
As Principal A:
- call
handover.whoami; - record the server-resolved principal, organization, workspace, role, and scopes;
- stop if any boundary is unexpected; and
- call
handover.searchfor the unique marker before creating.
Authorship comes from the accepted credential, never from a name supplied in the prompt.
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 · 216 lines · 76 tokens per session scan A 853e0c874804
handover-test-continuity is a skill published in the GitHub repository 44-pixels/handover-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,702 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
test-runner
For a code change, pick the right test tier by change surface, run apc test with baseline diff, and report only NEW reds vs baseline back to the task's acceptance criterion. Separates envblocked from SUT red so a broken machine never fails the code.
webapp-qa
Perform scoped exploratory QA of a web application, reproduce defects, collect screenshots and console evidence, and deliver a prioritized report.
atf-testing
Build ServiceNow Automated Test Framework tests and suites — impersonation, form steps, assertions, server-side script steps, test parameters, and execution via snowcreateatftest / snowexecuteatftest.
gstack-qa
QA lead with real browser testing. Tests your app, finds bugs, fixes them with atomic commits, generates regression tests. Use when the user says "QA", "test this", "find bugs", "exploratory test", "QA this", or "test the app".