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 jschulte/claude-plugins --skill whats-leftgit clone --depth 1 https://github.com/jschulte/claude-pluginsWrote 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/jschulte/claude-plugins/whats-left)<a href="https://agentmods.dev/skills/jschulte/claude-plugins/whats-left"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/whats-left/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/jschulte/claude-plugins/whats-left"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/whats-left.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 | $0.00082 | $0.02067 |
| Opus 5.5 | $0.00033 | $0.00827 |
| Sonnet 5.5 | $0.00016 | $0.00413 |
| Haiku 4.5 | $0.00008 | $0.00207 |
Grade A, and why
whats-left 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 24d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What's Left
Overview
The user wants two things: an honest account of what this session has actually accomplished, and the complete list of work still standing between here and done, in the order it should happen. They intend to answer with "yes please" and have you carry all of it out. So the remaining-work list is a plan you are about to execute, and anything you leave off it will not get done.
/recap tells the story in a few lines. This is the full ledger, followed by
an offer to finish the job.
The work can be anything: code, a release, an investigation, a document, data cleanup, a batch of emails, infrastructure. The procedure is the same; only the evidence and the finish line change. Where the steps below name git or CI, substitute whatever plays that role for the work at hand.
Procedure
-
Sweep the whole session, not just the recent part. Go back to the first message (and any compaction summary) and collect:
- every request the user made, including the small asides and the "oh, and also" ones
- everything you said you would do, come back to, or check later
- follow-ups you noticed and mentioned in passing
- failures, skipped steps, workarounds and TODOs left in code
- questions either side asked that never got an answer
- background tasks, agents and scheduled jobs you started
-
Check the claims against the real state. Memory of the session drifts, and a step that was "done" an hour ago may have been undone, or never landed. Run whatever applies, in parallel:
git status,git logagainst the base branch, unpushed commits, stashes- open PRs for the branch, their checks and unresolved review threads
- CI and deploy runs for what was pushed
- the tests, lint and typecheck for the changed code, if they have not run since the last edit
- any still-running background work
When a check cannot be run (a tool is switched off, no access, no network), skip it, carry on with the rest, and name the unchecked source in the report. One missing check never stops the sweep.
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.
- 24d ago First seen · 176 lines · 82 tokens per session scan A 73753bea8a23
whats-left is a skill published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 82 tokens to every session and 2,067 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-12.
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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.