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 spideynolove/claude-dotfiles --skill handoffgit clone --depth 1 https://github.com/spideynolove/claude-dotfilesWrote 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/spideynolove/claude-dotfiles/handoff)<a href="https://agentmods.dev/skills/spideynolove/claude-dotfiles/handoff"><img src="https://agentmods.dev/badge/skills/spideynolove/claude-dotfiles/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/spideynolove/claude-dotfiles/handoff"><img src="https://agentmods.dev/badge/skills/spideynolove/claude-dotfiles/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 | $0.00036 | $0.00522 |
| Opus 5 | $0.00018 | $0.00261 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
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 8d 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.
What it actually says
When to invoke
- Before ending a session when work is not complete
- When switching machines mid-task
- When you want Claude to summarize where things stand
What to write
Generate .claude/handoff.md with this exact structure:
# Handoff — <date>
## Current task
<one sentence: what was actively being worked on right now>
## Next steps
- [ ] <concrete next action — specific enough to act on without reading the whole conversation>
- [ ] <second action>
- [ ] ...
## Open questions
- <something that was about to be investigated but wasn't yet>
## Decisions made
- <decision>: <why — so it is not re-litigated on the next machine>
## Files in flight
- <path>: <what state it is in — partially done, needs review, etc.>
## Blockers
- <anything that stopped or slowed progress, if any>
Rules
- Current task: one sentence maximum. What was the active work, not the overall project goal.
- Next steps: must be concrete and immediately actionable. "Continue working on auth" is bad. "Add rate limit middleware to src/api/routes.ts after the auth check" is good.
- Decisions made: only decisions that could be re-litigated — architectural choices, rejected approaches. Not obvious things.
- Files in flight: only files with uncommitted or partial changes.
- Omit empty sections — if there are no blockers, omit the blockers section entirely.
After writing
mkdir -p .claude
# write the file, then:
git add .claude/handoff.md
git commit -m "chore: update handoff"
git push
This makes the handoff available on any machine that pulls the repo.
On the receiving machine
No action needed. context-loader.sh fires on session start and automatically injects .claude/handoff.md if it exists.
Clearing the handoff
Once work is complete (feature merged, task done), delete the file:
rm .claude/handoff.md
git add .claude/handoff.md
git commit -m "chore: clear handoff"
git push
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.
- 8d ago First seen · 74 lines · 36 tokens per session scan A 6d7d7f4222eb
handoff is a skill published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 522 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.