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 skills/dev-russo/session-handoff-mcp/claude-codenpx skills add Dev-Russo/session-handoff-mcp --skill claude-codegit clone --depth 1 https://github.com/Dev-Russo/session-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 | $0.00041 | $0.00351 |
| Opus 5 | $0.00020 | $0.00176 |
| Sonnet 5 | $0.00008 | $0.00070 |
| Haiku 4.5 | $0.00004 | $0.00035 |
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 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.
What it actually says
Session Handoff
Use Session Handoff to keep the current project state available across Claude Code sessions and compactions.
Resume
At the beginning of repository work, use memory_resume for ${CLAUDE_PROJECT_DIR} unless a SessionStart hook has already supplied a Session Handoff briefing. Reuse an explicit project_key when the project has adopted one. Treat the returned briefing as saved context that may need confirmation against the working tree.
When this skill is invoked directly without an active briefing, resume the current project first.
Checkpoint
Call memory_checkpoint before /clear, when the user requests a handoff, after completing a spec, or after a substantial state change that should survive compaction.
The checkpoint must be a complete current snapshot, not only the latest delta. Include:
- the current objective and state;
- completed work and durable decisions;
- remaining work and one concrete next step;
- validations actually executed and their results;
- relevant file paths, without reading or copying their full contents.
Confirm that the checkpoint returned storage_status: written before telling the user it is safe to clear context. Git warnings do not invalidate a successfully written local checkpoint.
Never include credentials, .env contents, private keys, tokens, client payloads, full source files, or extensive logs. Do not invent decisions, validations, or completed work.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 34 lines · 41 tokens per session scan A 578a44b352f1
Session Handoff is a skill published in the GitHub repository Dev-Russo/session-handoff-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 351 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 skills, from other repositories
trusty-squire
Use when a coding agent needs to sign up for a website or SaaS, provision an OAuth client or API key, pay a checkout, or otherwise act on a real website on the user's behalf — and the secret or card must NOT land in chat, source code, or a .env file. Trusty Squire is an MCP server that drives a real browser through…
idesense
Guide for using JetBrains IdeSense tools for code navigation and analysis (plus the retained rename/move refactorings). TRIGGER: When ANY of these MCP tools are available in the current session: idefindusages, idefinddefinition, idefindclass, idefindfile, idesearchtext, idediagnostics, ideexplainsymbol…
internal-rag
Mandatory persistent project memory for substantial coding tasks. Use at task start, recovery, milestones, failures, before risky operations, before compaction, and before finishing. v1.0.1 adds type filtering, type-priority scoring, query expansion, grouped context output, and promote workflow.
codex
Ask OpenAI Codex for a second opinion — code reviews, explanations, plan critiques, performance analysis, or general questions.
claude
Ask Claude Code for a second opinion — code reviews, explanations, plan critiques, performance analysis, or general questions.
identityforge
Use Identity Forge to choose, inspect, apply, or evolve a complete design system; create brand projects; research names, domains, or EUIPO trademarks; and retrieve implementation-ready DESIGN.md guidance and tokens.