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 vidhunnan/agentic-skills --skill handoff-generatorgit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/handoff-generator)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/handoff-generator"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/handoff-generator/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/vidhunnan/agentic-skills/handoff-generator"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/handoff-generator.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 | $0.00152 | $0.04934 |
| Opus 5 | $0.00076 | $0.02467 |
| Sonnet 5 | $0.00030 | $0.00987 |
| Haiku 4.5 | $0.00015 | $0.00493 |
Grade A, and why
handoff-generator 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 10d 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
handoff-generator
Produces a comprehensive project handoff: a portable Markdown document that captures the whole state of the work — what the project is, where it stands, how it got here, its features, decisions, what this session changed, open questions, referenced files, and next actions — so the work can continue on another surface (Claude.ai chat ↔ Claude Code) or with another person, without re-explaining anything. It is the shape of the two reference handoffs, not a one-line brief.
Three things make this skill different from a one-shot summarizer:
- It is comprehensive. The output is a full project handoff (~11 sections), not a five-line brief. It carries progress, a timeline, feature/component status, a changelog delta, and a near-verbatim log of the session conversation alongside decisions and next actions.
- It is bidirectional and surface-aware. The handoff can go chat→code, code→chat, or to some other destination (a fresh chat, a teammate, another Claude Code session). The section shape is the same on both surfaces; the sourcing differs — on Claude Code it is verified against the repo (git, changelog, decisions, PRDs); on Claude.ai it is drawn from the conversation. You decide the destination with the user and shape the handoff for it.
- It never runs autonomously. You always interview the user briefly first, gather the real intent and context, and only then generate. Do not rush straight to output.
Instructions
Step 0 — Detect your surface
You run on two surfaces that behave differently. Decide which one you are on before anything else, using Bash availability as the discriminator:
- Claude Code — you have a working Bash tool and a real project filesystem. If you can run a shell command, you are on Claude Code. Use the file + folder + resume behavior below.
- Claude.ai — you have no shell/Bash and no persistent project folder. If Bash is unavailable, you are on Claude.ai. Produce a downloadable artifact instead of writing a file; skip all folder and resume logic.
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.
- 10d ago First seen · 359 lines · 152 tokens per session scan A fbf9ec693c5d
handoff-generator is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 152 tokens to every session and 4,934 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…