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 aiya000/dotfiles --skill create-handoffgit clone --depth 1 https://github.com/aiya000/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/aiya000/dotfiles/create-handoff)<a href="https://agentmods.dev/skills/aiya000/dotfiles/create-handoff"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/create-handoff.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01163 |
| Opus 5 | $0.00036 | $0.00581 |
| Sonnet 5 | $0.00015 | $0.00233 |
| Haiku 4.5 | $0.00007 | $0.00116 |
Grade A, and why
create-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-handoff
Writes the handoff prompt for the next session, and puts it where read-handoff will find it on
its own. The point of the pair is that no one has to carry a path between sessions.
Where the file goes
Work the directory out in this order, and create it if it is not there:
~/tmp/claude-handoff/-- whenever~/tmpexists${TMPDIR:-/tmp}/claude-handoff/-- otherwise
Both are deterministic on purpose. A mktemp -d path cannot be found again by the next
session, which is the whole thing this pair exists to avoid. Only if neither can be created, fall
back to mktemp -d -- and then say the path loudly in your reply, because that is the one
case where the user does have to keep it.
⚠️ ~/tmp is read-only inside the Bash sandbox. Both the mkdir and the write need
dangerouslyDisableSandbox: true, so write the file with a quoted-heredoc cat > ... <<'EOF'
rather than the Write tool, which has no such option. (Adding ~/tmp to the sandbox's write
allowlist would remove the need -- see the update-config skill.)
File name: <project>-<YYYY-MM-DD-HHMM>.md
-
<project>is the repository the work is in, not the current directory:common=$(git rev-parse --path-format=absolute --git-common-dir 2>/dev/null) project=$( [ -n "$common" ] && basename "$(dirname "$common")" || basename "$PWD" )--git-common-diris what makes this right inside a git worktree: the directory there is calleddevelop, and the project is not. -
<YYYY-MM-DD-HHMM>comes fromdate +%Y-%m-%d-%H%M. Never overwrite an earlier handoff. The names sort chronologically, and the last one is whatread-handoffpicks.
What to write
Address the next session directly. It is not something to paste anywhere -- read-handoff
hands it over as instructions -- so drop any "paste this" preamble.
Write it in the language the session was held in.
Cover these, leaving out any that have nothing in them:
- 前提 -- working directory, branch, repository, and that
AGENTS.mdhas to be read first (read-agents-md), because it overrides habits and defaults - いちばん最初に -- the exact commands to get level (
git fetch,--ff-only), and where the branch stood when this was written: the SHA, and how far ahead of the release branch - 最優先の作業 -- what to do first and why: the reasoning, what was already settled with the user (in their own words where they settled it), and what is still open
- 未解決 / 返事待ち -- anything blocked on the user or on the outside world, including the exact question that was put to them
- 残っている Issue -- number and one line each
- 直近でやったこと -- SHA or PR number and one line each, so the next session can read the real diff rather than trust a summary
- コードの落とし穴 -- what cost time this session and would cost it again
- 運用まわりの注意 -- the tooling traps: which commands need what, which tests are flaky
- 最後に -- how the user is doing, and anything about their time and health
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.
- today First seen · 82 lines · 73 tokens per session scan A 112997cd5377
create-handoff is a skill published in the GitHub repository aiya000/dotfiles (19 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,163 once invoked, about $0.0004 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 2026-09-07.
Other skills, from other repositories
save-pipeline-memory
Capture a multi-step workflow into a timestamped pipeline memory after trial-and-error sessions. The core output is: (1) the final working commands saved as executable scripts (not bare shell commands), and (2) a structured markdown document separating the clean reproducible pipeline from the detours and pitfalls.…
insights
Analyze local Codex session history and generate a private usage report with workflow patterns, friction, recommendations, and quantitative statistics. Use when the user asks for Codex insights, a retrospective on how they use Codex, or a report based on local Codex sessions; do not use for billing, quotas, or API…
toil-offloading
Orchestrate decomposable workloads with native Codex team agents: the root agent analyzes, decides, partitions, integrates, and accepts while subagents execute bounded investigation, implementation, testing, and repetitive work. Use when the user asks for toil offloading, broad delegation, multi-project fan-out, or…
dotfiles
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec.
cmux-rebuild
Manage the user's durable dev sessions — zellij sessions on remote hosts (bonbon, taffy) reached over mosh, plus the local host's (trifle) own detached zellij sessions, surfaced as cmux tabs via ssh::durable / zellij::resume. Load when the user wants to rebuild/resurrect lost cmux durable surfaces after a cmux restart…
ask-for-help
Stop repeated unproductive retries and prepare a precise Codex escalation after five materially different failed attempts at the same blocker. Use when a task remains blocked despite repeated diagnosis or recovery; do not count ordinary tool calls or repeated variants of the same action as separate attempts.