Borrowing it
Nothing to install: this file belongs to white1024/agent-nextup. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/white1024/agent-nextup/main/.claude/skills/handoff-check/SKILL.mdgit clone --depth 1 https://github.com/white1024/agent-nextupWrote 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/white1024/agent-nextup/handoff-check)<a href="https://agentmods.dev/skills/white1024/agent-nextup/handoff-check"><img src="https://agentmods.dev/badge/skills/white1024/agent-nextup/handoff-check/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/white1024/agent-nextup/handoff-check"><img src="https://agentmods.dev/badge/skills/white1024/agent-nextup/handoff-check.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 | $0.00069 | $0.00743 |
| Opus 5.5 | $0.00028 | $0.00297 |
| Sonnet 5.5 | $0.00014 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
handoff-check 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 4d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
handoff-check — handover readiness checkpoint
What it is for: not tied to any particular feature — a way to confirm at any moment that a new session could pick this project up seamlessly.
Thin-shell principle: this skill only does a fast self-check in the main session plus delegation. It never copies checklists out of other skills or project documents, because a copy is a new source of drift.
Step 0: read CLAUDE.md at the project root (or the equivalent entry document) to find where the handover entry point and the record mechanism live. If the project has a more specialised skill for document sync or handover regression (check the reference in the entry document), delegate that step to it rather than redoing it with this file's generic default.
1. Self-check for loose ends (main session, seconds)
git status: uncommitted or unpushed work means dealing with that first (commit in batches per/wrap-up's conventions).- If the project has a health-check command, run it. It must come back clean; fix it before going further.
- Does the record match reality? Everything this session did — is it in the project's source of truth? Task statuses advanced? Settled decisions recorded? Pitfalls written down? Anything missing gets recorded right now, using the project's own record mechanism.
- Spot-check the claims: verifiable facts in the documents (counts, lists, commands) should match reality. If the project has a list of what to check against, follow it item by item — numbers hard-coded in prose are the usual drift point.
2. Substantial document changes -> adversarial review (skip if none)
If this round wrote a new document or rewrote a whole section, call the Skill tool with adversarial-review on those files: it sends a fresh-context agent to check them against reality item by item. Skip for small edits.
3. Cold-read acceptance (the heart of this skill)
- Send a read-only fresh-context agent that may start only from the project entry point (
CLAUDE.mdand the handover documents it points to) and must answer three questions — where are we / what is next / how was the previous step verified — and report anything unreadable, any broken link and any contradiction. - The main session judges the answers against reality. A wrong answer, or no answer, means the handover path is broken somewhere.
- Verification is not self-verification: judge against reality and the pass criteria, not against how the agent phrased things.
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.
- 4d ago Changed a1b64938283f
- 1mo ago First seen · 39 lines · 69 tokens per session scan A 06cef32b7d86
handoff-check is a skill published in the GitHub repository white1024/agent-nextup (2 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 743 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 2026-08-31.
Other skills, from other repositories
[object Object]
Skill "[object Object]" from microsoft/apm, covering what this package does, getting started, available primitives and included workflows.
apm-usage
Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any apm CLI command.
dev-orchestrator
Coordinate development through 16 phases (0-15) across planning, implementation, verification, and review gates when a task needs multiple dependent steps or consequential decisions.
frontend-state-management
SocialApp user frontend state management — TanStack Query, Zustand, IndexedDB persistence, cache invalidation, multi-account isolation.
bot-reviewer
Review Telegram, Discord, Slack, and other chat bot code for interaction safety, authorization, state, delivery, and resilience using the actual platform and framework contract. Read-only review with explicit coverage and unverified gates.
design-system-reviewer
Review selected UI components, tokens, themes, and public component APIs against the project's actual design system, approved design, and consumer contracts.