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/gh33k/session-plugin/handoffnpx skills add gh33k/session-plugin --skill handoffgit clone --depth 1 https://github.com/gh33k/session-pluginWhat 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 | $0.00009 | $0.00576 |
| Opus 5 | $0.00005 | $0.00288 |
| Sonnet 5 | $0.00002 | $0.00115 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
session:handoff
Generate a copy-pasteable continuation prompt for starting a new chat session with full context.
Instructions
When the user runs /session:handoff, generate a handoff prompt that can be pasted into a new Claude session.
1. Gather Current Context
Collect information from multiple sources:
# Get project info
cat .project/state.md 2>/dev/null
# Get continuation info if available
cat .context/continuation.md 2>/dev/null
# Get in-progress tasks
bd list --status=in_progress 2>/dev/null
# Get ready tasks
bd ready --limit=5 2>/dev/null
# Get recent git activity
git log --oneline -5 2>/dev/null
2. Generate Handoff Prompt
Create a structured prompt in this format:
Continue developing [project name].
Project: [absolute path]
Repo: [git remote URL if available]
## Context
[Read ARCHITECTURE.md or relevant docs for design decisions]
[Key files or components being worked on]
## Ready Tasks (run `bd ready` to verify)
- [task-id]: [title]
## This Session's Work
[Brief summary of what was accomplished]
## Suggested Next Steps
1. [Most important next action]
2. [Secondary action]
Use subagents for parallel implementation where possible.
3. Output Format
Present the handoff prompt in a copyable format:
=== HANDOFF PROMPT (copy below this line) ===
[Generated prompt content]
=== END HANDOFF PROMPT ===
4. Options
/session:handoff --focus="X"- Focus on specific feature/session:handoff --minimal- Shorter prompt with essentials only/session:handoff --files- Include recently modified files
Example
User: /session:handoff
Assistant: Generating handoff prompt...
=== HANDOFF PROMPT (copy below this line) ===
Continue developing my-project.
Project: /path/to/my-project
Repo: https://github.com/user/my-project
## Context
Read ARCHITECTURE.md for design decisions.
Currently implementing user authentication.
## Ready Tasks (run `bd ready` to verify)
- v2-abc: Add login endpoint
- v2-def: Create auth middleware
## This Session's Work
1. Set up project structure
2. Implemented basic routing
## Suggested Next Steps
1. Complete login endpoint (v2-abc)
2. Add session management
Use subagents for parallel implementation where possible.
=== END HANDOFF 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.
- yesterday First seen · 113 lines · 9 tokens per session scan A db51027db92f
handoff is a skill published in the GitHub repository gh33k/session-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 576 once invoked, about $0.0000 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
agent-native-architecture
Design agent-native architectures where agents are first-class citizens. Use when building autonomous agents, MCP tools, or self-modifying systems.
lavra-ceo-review
CEO/founder-mode plan review -- challenge premises, validate business fit, run 10-section structured review.
lavra-review
Perform exhaustive code reviews using multi-agent analysis and ultra-thinking.
dspy-ruby
Build type-safe LLM applications with DSPy.rb. Use when implementing AI features, LLM signatures, agent systems, or prompt optimization in Ruby.
lavra-brainstorm
Explore requirements and approaches through collaborative dialogue before planning.
lavra-knowledge
Capture solved problems as knowledge entries for fast recall. Use when a solution should be preserved for future sessions.