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/etr/groundwork/handoffnpx skills add etr/groundwork --skill handoffgit clone --depth 1 https://github.com/etr/groundworkWhat 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 | $0.00034 | $0.00988 |
| Opus 5 | $0.00017 | $0.00494 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Overview
A handoff is a baton, not a backpack: it carries just enough for the next session to resume, and points at everything else. The receiving agent has none of this conversation's context, so the document is the entire transfer — but it must stay compact, or it competes for the very context budget it is meant to preserve.
Core principle: Reference artifacts by path or URL; never duplicate their content into the handoff.
When to Use
- Ending a session with work still in progress
- Handing a task to another agent or person
- Approaching context compaction and wanting a durable resume point
The optional [focus] argument shapes the summary toward the next objective (e.g. /groundwork:handoff finish the auth refactor). Without it, summarize toward the most recent active thread.
Process
1. Locate work products
Gather what already exists rather than restating it. Run as needed:
git rev-parse --abbrev-ref HEAD # current branch
git log --oneline -5 # recent commits
git status --short # uncommitted changes
git diff --stat # scope of working-tree changes
Note paths to PRDs, plans (.groundwork-plans/), ADRs, specs, and any issue/PR URLs. These become links, not content.
2. Compose the document
Write to a temp path outside the repo, slug derived from the focus:
SLUG=$(echo "${ARGUMENTS:-session}" | tr '[:upper:] ' '[:lower:]-' | tr -cd 'a-z0-9-' | cut -c1-40)
OUT="${TMPDIR:-/tmp}/groundwork-handoff-${SLUG}.md"
The document has exactly these sections:
| Section | Contents |
|---|---|
| Summary | Focused recap of the conversation, tailored to the next objective. Decisions made and why; dead ends ruled out. |
| State | What is done, what is in progress, what is blocked. Branch and commit refs. |
| Next objective | The single thing the receiving session should accomplish next. |
| Artifacts | Bulleted links — paths, branch names, commit SHAs, diffs, issue/PR URLs. References only. |
| Suggested skills | Which Groundwork skills to invoke next, and a pointer to [[using-groundwork]] to map any remaining work. |
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.
- 2d ago First seen · 90 lines · 34 tokens per session scan A 9399d8636409
handoff is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 21d ago), licensed MIT. It adds 34 tokens to every session and 988 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…