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 koolamusic/claudefiles --skill handoffgit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/koolamusic/claudefiles/handoff)<a href="https://agentmods.dev/skills/koolamusic/claudefiles/handoff"><img src="https://agentmods.dev/badge/skills/koolamusic/claudefiles/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/koolamusic/claudefiles/handoff"><img src="https://agentmods.dev/badge/skills/koolamusic/claudefiles/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00874 |
| Opus 5.5 | $0.00028 | $0.00350 |
| Sonnet 5.5 | $0.00014 | $0.00175 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Write a handoff document that lets a fresh agent continue this work cold. The reader has zero context from this conversation — the handoff is their entire briefing.
Process
-
Gather state. Run these in parallel:
git log --oneline -20(recent commits)git status(working tree)git branch --show-current(active branch)- Check for
.jira/CURRENT(active sprint) - Check for
.project/PROJECT.md(project context) - Check for
.workspacerc(studio workspace)
-
Determine the output path.
- If
.workspacercexists: read the workspace path, write to<workspace>/handoff.md - If
.jira/exists: write to.jira/sprints/<active-slug>/HANDOFF.md - Otherwise: write to the OS temp directory (
$TMPDIRor/tmp)
- If
-
Write the handoff using the structure below. If the user passed arguments, treat them as a description of what the next session will focus on and tailor accordingly.
-
Don't duplicate. Reference existing artifacts (CONTEXT.md, PLAN.md, RESEARCH.md, PRDs, issues) by path or URL. The handoff points to them — it doesn't restate them.
-
Redact secrets. Strip API keys, passwords, tokens, PII. If a secret is relevant context, note its purpose without the value.
Handoff structure
# Handoff — <date> — <one-line mission>
## Repo state
- **Branch:** <branch>
- **Clean:** yes/no (if dirty: what's uncommitted and why)
- **Active sprint:** <slug> or none
- **Last meaningful commit:** <hash> <subject>
## Your role
<ORCHESTRATOR or IMPLEMENTER — and what that means for this session>
## Mission
<2-3 sentences: what you're trying to accomplish and why it matters>
## Scope
<Numbered list of scope items. Each item: what it is, rough effort, status (done/in-progress/not-started)>
## Locked decisions
<Decisions already made that the next session must not revisit. Reference D-XX from CONTEXT.md if available.>
## Open gates
<Decisions still pending that the next session needs to resolve before proceeding.>
## Dispatch sequence
<If orchestrating: recommended wave/agent breakdown. Which items can parallelize, which are sequential.>
## Operational practices
<Branch naming, commit conventions, PR process, testing expectations — anything non-obvious about how this repo works.>
## Pickup checklist
1. Read this handoff
2. <specific first action>
3. <specific second action>
...
## Not your problem
<Explicit scope boundaries: what's out of scope and should not be touched.>
## Suggested skills
<Skills the next session should invoke, e.g. /grill, /jira:plan, /spawn>
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.
- 1mo ago First seen · 87 lines · 69 tokens per session scan A b429113986c9
handoff is a skill published in the GitHub repository koolamusic/claudefiles (121 stars, last pushed 11d ago), licensed MIT. It adds 69 tokens to every session and 874 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 2026-08-30.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.