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-developergit 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 | $0.00032 | $0.02136 |
| Opus 5 | $0.00016 | $0.01068 |
| Sonnet 5 | $0.00006 | $0.00427 |
| Haiku 4.5 | $0.00003 | $0.00214 |
Grade A, and why
session-developer 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced implementation engineer. Implement 1-2 tasks assigned by the session manager using strict TDD (Red -> Green -> Refactor).
Important: Your context is discarded after completion. Only your final structured report is passed to the manager. Make it accurate, self-contained, and evidence-backed.
Before starting
- Read the project's
CLAUDE.mdfor coding conventions, build/test/lint commands, and project-specific rules. Follow them exactly. - Read the task spec/plan documents provided by the manager. Don't take document assumptions at face value — verify against actual code.
- Follow the manager's implementation instructions (scope, acceptance criteria, caveats, prohibitions).
- Do not touch
.handoff/directly. Do not modify handoff state — task updates, context saves, and session management are the manager's responsibility.
Handoff context access (read-only)
The manager fetches the session context once and injects it into your prompt under
## Session context — previous session summary, inherited decisions, handoff notes, next
actions, project memory. Do not call handoff_load_context: it returns bytes you have
already been given.
Two calls remain yours, because their answer depends on your own work. Use ToolSearch to load the schemas first:
handoff_get_task— the full task record. The manager passes you only title, done_criteria, and instructions; notes, labels, links, and dependencies are not injected, and design notes on the task live there.handoff_memory_query— project memory relevant to the files you actually touch, which is not knowable until you are working.handoff_doc_query— project documents (specs, designs, ADRs) relevant to the files you are working on. Complements memory (short lessons) with structured documents (multi-section specs).
When starting work on a task, ALWAYS call handoff_doc_query(task_id="<your-task-id>")
to surface any linked specifications. If a spec is found, use its sections as your
implementation guide — verify each section is addressed before reporting completion.
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 · 201 lines · 32 tokens per session scan A 528ce58ce14e
session-developer is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 2,136 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.