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 jqaisystems/jqai-ai-skills --skill session-handoffgit clone --depth 1 https://github.com/jqaisystems/jqai-ai-skillsWrote 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/jqaisystems/jqai-ai-skills/session-handoff)<a href="https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/session-handoff"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/session-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/jqaisystems/jqai-ai-skills/session-handoff"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/session-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 | $0.00093 | $0.00661 |
| Opus 5 | $0.00046 | $0.00331 |
| Sonnet 5 | $0.00019 | $0.00132 |
| Haiku 4.5 | $0.00009 | $0.00066 |
Grade A, and why
session-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 11d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff
Context dies between sessions. The next session re-reads files, re-discovers decisions, and re-hits the same trap that cost an hour last time. This skill freezes the session's working state into one document built to be read cold.
Step 1: Mine the session
Extract from the current conversation, not from memory of what should have happened:
- What was accomplished: only things actually finished and verified. Half-done work is listed as half-done.
- Decisions made and why: especially decisions that reversed an earlier approach. The "why" is the part the next session cannot reconstruct.
- What is in progress: exact state, which file, which step.
- Next steps: concrete and ordered, with the first one precise enough to start typing immediately.
- Gotchas: everything that failed and how it was fixed, environment quirks, commands that need specific flags, things that look broken but are fine.
- Key paths and commands: the files that matter and the exact commands to run (build, test, deploy, resume).
Step 2: Write the handoff
Default target: START_HERE.md in the project root (or append a dated section to an existing one, newest at the top). Format:
# Start Here: <date>
## TL;DR
Two sentences: where the project is, and the single next action.
## Done this session
## In progress
Exact state, file, and step for each item.
## Next steps (in order)
1. The first one must be executable immediately, with the exact command or file.
## Decisions and why
## Gotchas
What burned time this session, so it does not burn time again.
## Key paths and commands
Step 3: Verify readability cold
Reread the document as someone with zero context: no session shorthand, no "the fix we discussed", no codenames invented mid-conversation. Every reference names its file. If a next step depends on a decision, the decision is in the document too.
On resume
When a new session starts with "where did we leave off": read START_HERE.md, confirm the state still matches reality (files may have changed since), and start on next step 1. Flag divergence instead of following a stale plan.
What ships with it
1 file 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.
- 11d ago First seen · 62 lines · 93 tokens per session scan A 62f1fac82ef6
session-handoff is a skill published in the GitHub repository jqaisystems/jqai-ai-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 661 once invoked, about $0.0005 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
baoyu-wechat-summary
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory…
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
update-turbo
Update installed Turbo skills from the local repo with a dynamic changelog, conflict resolution for customized skills, and guided user experience. Use when the user asks to "update turbo", "update turbo skills", "reinstall turbo", or "upgrade turbo".
herdr
Control Herdr, the terminal multiplexer for coding agents. Use when the user mentions Herdr or another skill delegates pane control, including concise pane naming, inspection, commands, and agents. Integrates with vd:worktree, vd:codex-workflow, and vd:ultracook. Requires HERDRENV=1.
superwhisper
Operate the official Superwhisper CLI and MCP to search or read dictation history, diagnose pronunciation and raw-versus-processed transcription errors, detect unwanted expansion of short utterances, inspect usage, build standups or commitment reviews, and manage vocabulary or snippets with approval. Use when the user…
gog
Manage Google Workspace from the CLI via gog: Gmail, Drive, Calendar, Sheets, Docs, Chat, Tasks, and Admin. Invoke with --account (any account in the local registry) and --user person|sa. Use when the user mentions gmail, drive, calendar, sheets, docs, workspace, gog, email, files, events, or a configured account.