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/shipnpx skills add etr/groundwork --skill shipgit 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 | $0.00036 | $0.00835 |
| Opus 5 | $0.00018 | $0.00417 |
| Sonnet 5 | $0.00007 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
ship 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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship
Orchestrator for the ship phase — the last leg of the lifecycle, after the change is built, validated, and reviewed. It sequences the ship disciplines and stops at a human go/no-go before anything reaches users.
Step 1: Confirm Validation and Review Passed
Shipping presupposes a clean change. Confirm both gates already cleared:
- Validation passed — see [[validate]].
- Review passed — see [[review-pr]].
Check for evidence (a green validation run, an approved PR). If you cannot confirm either, stop and ask the user to run [[validate]] / [[review-pr]] first. Do not re-run them here; this skill assumes they are done.
Step 2: Sequence the Ship Disciplines
Dispatch the two disciplines in order via the Skill tool. Each is dual-tier, so this leaf may call them. Do not parallelize — the rollout depends on the instrumentation.
(Architecture decisions are recorded earlier, during design-architecture — there is no decision-capture step here.)
Skill(skill="groundwork:instrument-observability")— make the change observable (structured logs, RED metrics, trace spans, symptom alerts). Run before rollout: the rollout's monitoring window watches these signals.Skill(skill="groundwork:staged-rollout")— produce the pre-launch checklist, feature-flag gating, the staged/canary ramp, and the written rollback plan.
Carry each skill's verification result forward. If any reports its Verification incomplete, surface that to the user at Step 3 rather than silently proceeding.
Step 3: Final Go / No-Go Gate
Before any outward-facing deploy step (flipping the canary flag on, promoting a stage, releasing), stop and ask the user with AskUserQuestion:
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.
- yesterday First seen · 69 lines · 36 tokens per session scan A 6d077f766615
ship is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 20d ago), licensed MIT. It adds 36 tokens to every session and 835 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…