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 HirogaKatageri/hirokata --skill daily-handoffgit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/daily-handoff)<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/daily-handoff"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/daily-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/hirogakatageri/hirokata/daily-handoff"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/daily-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 | $0.00155 | $0.02471 |
| Opus 5 | $0.00077 | $0.01236 |
| Sonnet 5 | $0.00031 | $0.00494 |
| Haiku 4.5 | $0.00015 | $0.00247 |
Grade A, and why
daily-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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily Handoff
Turn the last 24 hours of scattered activity — pull requests, review comments, AI coding sessions, and half-finished local work — into one handoff document a teammate can read without asking follow-up questions.
Purpose
At the end of a working day the record of what happened is spread across GitHub, several local checkouts, and the transcripts of whatever AI coding tools were used. None of those tell a colleague what is finished, what is waiting on them, and what to pick up next.
This skill collects all four sources, sorts them into four buckets, and writes the result as plain-language markdown aimed at a reader who was not there.
Who the document is for
Write for a teammate who does not know this work. That single decision drives every other rule in this skill:
- They do not know the codebase, so name things by what they do, not by their symbol names.
- They do not know the jargon, so spell it out. See
references/plain-language.md. - They cannot ask a follow-up question, so anything they must act on has to be complete on the page.
Workflow
Step 1 — Set the window and the output path
Default to a 24-hour lookback and today's local date.
HOURS=24
TODAY=$(date +%Y-%m-%d)
OUT="$HOME/${TODAY}-handoff.md"
Honour the hours, scan-root and output arguments if the user supplied them. If the
user asked for "yesterday" or "this week", translate that into hours (24, 168) rather than
inventing a different window.
Step 2 — Run the three collectors
They are independent. Run them together, and do not stop if one comes back empty — an empty section is itself information.
SKILL_DIR="<this skill's directory>"
TMP=$(mktemp -d)
bash "$SKILL_DIR/scripts/collect-github.sh" "$HOURS" > "$TMP/github.json"
bash "$SKILL_DIR/scripts/collect-repos.sh" "$HOME/Projects" "$HOURS" > "$TMP/repos.json"
python3 "$SKILL_DIR/scripts/collect-sessions.py" --hours "$HOURS" > "$TMP/sessions.json"
What ships with it
5 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.
- 2d ago First seen · 196 lines · 155 tokens per session scan A a422083b7406
daily-handoff is a skill published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 3d ago), licensed MIT. It adds 155 tokens to every session and 2,471 once invoked, about $0.0008 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 2026-09-09.
Other skills, from other repositories
crm-management
Use when an internal 101 goal must manage CRM pipelines, stages, deals, or distribution rules through the current CRM API.
estimate-management
Use when an internal 101 goal must find, read, create, or edit one or many estimates through the existing event API, including sourced or manual positions and their dates.
project-management
Use when an internal 101 goal must create or edit a project, select its customer or price list, manage project expense categories, or copy category settings from another project.
task-management
Use when an internal 101 goal must list, read, open, update, or comment on tasks, including the interactive task detail widget.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…