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/setup-reponpx skills add etr/groundwork --skill setup-repogit 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 | $0.00030 | $0.00699 |
| Opus 5 | $0.00015 | $0.00349 |
| Sonnet 5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
setup-repo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Repository Skill
Configures the repository structure for Groundwork. Detects or asks whether this is a single-project repo or a monorepo, and creates .groundwork.yml for monorepos.
Workflow
Step 1: Detect Repository Structure
Look for common monorepo patterns:
- Multiple directories with their own
package.json,go.mod,Cargo.toml, etc. - Common monorepo directories:
apps/,packages/,services/,projects/ - Existing
specs/directory (suggests single-project) - Workspace configuration files (
pnpm-workspace.yaml,lerna.json,turbo.json)
Step 2: Ask User
Use AskUserQuestion to confirm:
"I've analyzed your repo structure. Is this:"
- Single project — One project, specs at the repo root
- Monorepo — Multiple projects, each with their own specs
If monorepo indicators were found, mention them:
"I noticed [apps/, packages/, workspace config], which suggests a monorepo structure."
Step 3: Configure
If single project:
- No config file needed
- Ensure
.groundwork-plans/is in.gitignore(add it if missing) — work-on writes per-task plan files there. - Confirm: "Single-project mode. Specs will be stored in
specs/at the repo root." - Proceed — no
.groundwork.ymlcreated.
If monorepo:
- Ask which directories are projects. Suggest based on detected structure.
- Use
AskUserQuestionwith multi-select to confirm project list. - Create
.groundwork.yml:
version: 1
projects:
<project-name>:
path: <relative/path>
<project-name>:
path: <relative/path>
- Ensure
.groundwork.localand.groundwork-plans/are in.gitignore(add any missing entries)..groundwork-plans/is where work-on writes per-task plan files. - Ask which project to start with using
AskUserQuestion. - Set project context:
GROUNDWORK_PROJECT=<name>andGROUNDWORK_PROJECT_ROOT=<path>
Step 4: Persist Selection
For monorepo mode, persist the selection to .groundwork.local at the repo root (gitignored) so it survives session restarts.
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 · 78 lines · 30 tokens per session scan A 5e94e72c9c05
setup-repo is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 21d ago), licensed MIT. It adds 30 tokens to every session and 699 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.