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 nagarjuna-msr/fable-god-mode --skill session-handoffgit clone --depth 1 https://github.com/nagarjuna-msr/fable-god-modeWrote 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/nagarjuna-msr/fable-god-mode/session-handoff)<a href="https://agentmods.dev/skills/nagarjuna-msr/fable-god-mode/session-handoff"><img src="https://agentmods.dev/badge/skills/nagarjuna-msr/fable-god-mode/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/nagarjuna-msr/fable-god-mode/session-handoff"><img src="https://agentmods.dev/badge/skills/nagarjuna-msr/fable-god-mode/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 | $0.00234 | $0.02393 |
| Opus 5 | $0.00117 | $0.01196 |
| Sonnet 5 | $0.00047 | $0.00479 |
| Haiku 4.5 | $0.00023 | $0.00239 |
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 10d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff — natural pause → audited handoff doc → one-liner resume
Heavy sessions degrade and cost more: past roughly ~500k tokens of history the cache churn, compaction losses, and re-reading overhead all grow, and billing grows with them. The cure is a clean cut: pause at a NATURAL boundary, externalize the state so a zero-context successor can continue with minimal loss, audit that externalization with a fresh set of eyes, and give the human ONE line to paste into the fresh session. This skill is that procedure. It is generic — discover the project's own conventions and adapt; never assume a specific domain, agent roster, or doc layout.
Two hard rules up front:
- Never an abrupt pause. If work is running, find the natural boundary first (Step 0).
- The deliverable is a ONE-LINER, not a wall of prompt. The wall lives inside the handoff doc; the one-liner points at it.
Step 0 — Find the natural pause (only if work is in flight)
Inventory everything live: background subagents, workflows, background bash, external jobs (CI, deploys, paid batches). Then:
- Nothing running → you are already at the boundary; go to Step 1.
- Bounded work mid-flight (a build/review/gate cycle, a batch that lands soon) → announce in ONE line what you are waiting for, let it land, close out ONLY what is already in motion (e.g. the review round that just returned), and start nothing new. The boundary = the current cycle's verdict/receipt landing on disk.
- Long/unbounded work (hours-long runs) the user wants to leave running or that cannot finish before the pause → do NOT kill it unless the user says so. Instead externalize its resume recipe: receipts/checkpoint paths on disk, the exact restart command (e.g. a workflow script path — note that same-session run-ids and agent ids DIE with the session, so a successor needs the from-disk restart form), and what "done" will look like. A new session can never message this session's agents — anything only they know must be written to disk NOW.
- If the user asked to pause "when it arrives", state the boundary you're waiting on in one line and wait. One line only.
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.
- 10d ago First seen · 144 lines · 234 tokens per session scan A 4f02b6a99714
session-handoff is a skill published in the GitHub repository nagarjuna-msr/fable-god-mode (10 stars, last pushed 1mo ago), licensed MIT. It adds 234 tokens to every session and 2,393 once invoked, about $0.0012 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
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…