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/dryvist/claude-code-plugins/handoffnpx skills add dryvist/claude-code-plugins --skill handoffgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat 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 | $0.00116 | $0.01505 |
| Opus 5 | $0.00058 | $0.00753 |
| Sonnet 5 | $0.00023 | $0.00301 |
| Haiku 4.5 | $0.00012 | $0.00151 |
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 2d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Produce one artifact a fresh session can run cold: a short goal statement and a long full prompt. The new session sees none of the current conversation, so the artifact must stand alone.
The goal statement is capped because a harness goal field consumes it; /goal
owns that cap. The full prompt is the first message of the new session and has
no cap.
State warning: TaskList contents, plan checklist state, and any git state all drift. Re-gather them when you build the handoff. Never copy state from earlier in this conversation.
When to use
- Forking unfinished work to a fresh session (the common case).
- Standing up an orchestrator or subagent that starts with no context.
- Inside
/wrap-up: Path A's follow-up prompt and Path B's resume blocks both call this skill instead of emitting a prompt with no goal.
Step 1: Gather live state
Do not trust memory. Collect what exists; skip what does not.
Always available:
- The plan file path (from the plan-mode
## Plan File Info:reminder) and its open checklist items with line numbers. TaskList— tasks whosestatus != "completed".- The one or two files a fresh session must read first to be dangerous.
Version-control enrichment — only when the cwd is a repository. Guard it:
git rev-parse --is-inside-work-tree >/dev/null 2>&1
When that succeeds, add: git status, current branch, and any worktree paths
the work lives in; open PRs via gh pr list. Capture full URLs, never bare
#123. Tracked follow-up work is not a GitHub issue — its identifier comes from
track-followups, not from gh.
When it fails, skip the whole block and say so in the emitted artifact ("no repository at this cwd; branch and PR state omitted"). A handoff without git facts is still a handoff — the reading list, rules, and pitfalls carry it.
Ticket enrichment — only when the tools are configured. If mcp__zammad__*
is available this session, check with zammad_search_tickets; otherwise rely on
ticket numbers already known from context. Capture full ticket URLs
($ZAMMAD_URL/#ticket/zoom/<id>), never a bare #17053 — same rule as GitHub,
extended to Zammad.
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.
- 2d ago First seen · 140 lines · 116 tokens per session scan A 6d47ff35cdf1
handoff is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 1,505 once invoked, about $0.0006 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
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
mcp-server
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…
ratatui-ruby
This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…
dragonruby
This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…