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/groundwork-helpnpx skills add etr/groundwork --skill groundwork-helpgit 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 | $0.00020 | $0.00901 |
| Opus 5 | $0.00010 | $0.00451 |
| Sonnet 5 | $0.00004 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
groundwork-help 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Groundwork Help
Lists all available skills and agents provided by the Groundwork plugin. Every Groundwork
capability is a skill, invoked either as /groundwork:<name> or automatically by the model.
Workflow
Step 1: Gather Component Information
Read the plugin manifest and scan directories:
- Read
${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.jsonfor overview - Scan
${CLAUDE_PLUGIN_ROOT}/skills/for available skills (each<name>/SKILL.md) - Scan
${CLAUDE_PLUGIN_ROOT}/agents/for available verification/research agents
Step 2: Extract Descriptions
For each skill, extract the name and description from the SKILL.md YAML frontmatter. Note its
invocation tier from the frontmatter:
disable-model-invocation: true→ user-only slash workflowuser-invocable: false→ hidden library skill (model/other-skill use only)- neither → dual (user slash + model auto)
Step 3: Group and Present
Present the skills grouped by purpose. Hide user-invocable: false library skills from the
user-facing list (they are internal). Example grouping:
User-invocable skills (/groundwork:<name>)
List skills organized by purpose:
Spec-Driven Development:
/groundwork:design-product- Define product requirements/groundwork:design-architecture- Design technical approach/groundwork:create-tasks- Generate implementation tasks
Task Execution:
/groundwork:work-on [N]- Work on a specific task by number/groundwork:work-on-next-task- Work on the next task/groundwork:plan-task [N or description]- Plan a task or feature without implementing/groundwork:implement-task [N or plan-path]- Implement a previously planned task
Quick Development:
/groundwork:build-unplanned [description]- Build a feature from description with worktree isolation and TDD
Sync & Alignment:
/groundwork:source-product-specs-from-code- Sync specs with code changes/groundwork:source-architecture-from-code- Update architecture docs/groundwork:check-specs-alignment- Verify spec alignment (full audit)/groundwork:split-specs- Convert single-file PRD into directory format/groundwork:split-architecture- Convert single-file architecture doc into directory format
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 · 97 lines · 20 tokens per session scan A b4135762c0f6
groundwork-help is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 20d ago), licensed MIT. It adds 20 tokens to every session and 901 once invoked, about $0.0001 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…