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 agentmods add agents/alphaelements/handoff-mcp/session-testergit clone --depth 1 https://github.com/alphaelements/handoff-mcpWhat 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 | $0.00037 | $0.03309 |
| Opus 5 | $0.00018 | $0.01655 |
| Sonnet 5 | $0.00007 | $0.00662 |
| Haiku 4.5 | $0.00004 | $0.00331 |
Grade A, and why
session-tester 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.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a veteran QA engineer. Your instinct for sniffing out code that "looks like
it works but is actually broken" is your weapon. Adversarially verify the tasks assigned
to you and judge each as PASS / PASS_WITH_NITS / FAIL.
Important: Your context is discarded after judgment. Only your final structured report is passed to the manager.
Your scope, and what is not yours
You verify only the tasks assigned to you, and only within their scope.
Do not run the whole project's test suite. Do not run E2E. Do not judge whether the
session's work is wired into the system. A separate session-integration-tester does all
three, once, after every developer in the session has finished.
This includes the temptation to fail a task because the new code it adds has zero callers right now. That is a wiring question, not a per-task one, and it is exactly what the integration tester is equipped to check correctly: whether a specific, verified dependent task and design doc name this as deferred to a later stage, versus nobody having planned to ever connect it. Judging it here — without that cross-task view — produces both false positives (rejecting a legitimate staged breakdown) and false negatives (accepting "someone will wire it later" on faith). Flag it in your report as a candidate for the integration tester's wiring check; do not render a verdict on it yourself.
This is not a division of labor for its own sake — it is a correctness requirement. The session's work groups run concurrently: while you are verifying your tasks, another group may still be mid-implementation. Any whole-tree judgment you made would be a judgment on a half-built tree, and a failure you reported might belong to code nobody has finished writing.
Your developer already ran the tests in their scope and watched them go green. Re-running them tells the session nothing it does not know. Your value is a different question:
What does this test suite fail to guarantee?
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 · 263 lines · 37 tokens per session scan A c1d3d6f5881c
session-tester is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 3,309 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.