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 agentmods add skills/sandsower/beislid/handoffnpx skills add sandsower/beislid --skill handoffgit clone --depth 1 https://github.com/sandsower/beislidWrote 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/sandsower/beislid/handoff)<a href="https://agentmods.dev/skills/sandsower/beislid/handoff"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/handoff.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.01343 |
| Opus 5 | $0.00037 | $0.00672 |
| Sonnet 5 | $0.00015 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00134 |
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 3d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Create a paste-ready opening prompt for another agent/session/worktree. For repo-local isolation policy and cleanup paths, see docs/worktree-isolation.md. This skill is read-only in the parent workspace except for copying text to the local clipboard.
Use this when:
- Work is being split across parallel sessions or worktrees
- The user wants a scoped context packet for another coding agent
- The user says things like "handoff frontend", "handoff backend", "handoff QA", or "make a handoff for the migration"
Do not use this when:
- Resuming the same work in the same session — use a dedicated resume workflow if available
- Starting a fresh ticket from the tracker — use
kickoff - Saving long-term session memory — use
mementoif available
Process
1. Determine the slice
If the user's request includes a clear slice, proceed. Clear slices include:
- domain words: frontend, backend, mobile, QA, test, migration, infra, docs
- named files, directories, components, services, or APIs
- an explicit task statement
If the user only says "handoff" or gives vague scope like "some of this", ask one clarifying question:
What slice should I hand off — frontend, backend, QA, migration, or something else?
Do not gather context until the slice is clear.
2. Gather read-only workspace state
Run simple read-only commands. Avoid compound commands when the host prompts for bash permissions.
Required:
pwd
git branch --show-current
git status --short
git diff --stat
Optional, if relevant and cheap:
git log --oneline -5
find plans -maxdepth 2 -type f
Only read plan/spec/design files if they are directly relevant to the requested slice. Do not read or paste full diffs.
3. Extract explicit context
Build the handoff from:
- the user's stated goal
- the requested slice
- explicit decisions made in this conversation
- relevant written artifacts you read
- current git state from the required commands
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.
- 3d ago First seen · 179 lines · 75 tokens per session scan A 181a19cb6bb1
handoff is a skill published in the GitHub repository sandsower/beislid (10 stars, last pushed 4d ago), licensed MIT. It adds 75 tokens to every session and 1,343 once invoked, about $0.0004 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…