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 skills add mhmdreza-rafiei/agent-tools --skill groundworkgit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/groundwork)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/groundwork"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/groundwork/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/groundwork"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/groundwork.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00132 | $0.02993 |
| Opus 5 | $0.00066 | $0.01496 |
| Sonnet 5 | $0.00026 | $0.00599 |
| Haiku 4.5 | $0.00013 | $0.00299 |
Grade A, and why
groundwork 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 8d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/groundwork
Build and continuously improve the shared context system every other skill reads from and writes to — the single source of truth that keeps stateless agents consistent. Groundwork does not just create the context once: every time it runs, and every time the context is used, the context should get more detailed, more accurate, and better structured.
Self-improving context (core principle)
The context is a living thing, not a one-time scaffold.
- On first run, capture the most accurate, specific picture you can.
- On every
/groundwork update— and whenever an agent works with the context — deepen and sharpen it: add detail learned since, correct anything that drifted, tighten vague sections, fill> TODO:markers, and improve structure and wording. - An update must never make the context thinner or vaguer than before. "Better" means more true and more useful, not more words. Cut filler; add verified specifics.
Automation-first
Infer from the project and proceed. State assumptions in one short line as you go. Ask only when genuinely blocked, or before something destructive (overwriting a human-edited context). Never interrogate.
Verify before you encode (trust code over docs)
Treat docs, READMEs, comments, and old files as claims, not truth — they are often stale or abandoned. Verify against what the code actually does: where a doc and the code disagree, trust the code and note the doc as stale. Watch for stale signals (old timestamps, references to removed files/APIs, deps named in docs but missing from the manifest). When you cannot confirm something, mark it > NEEDS VERIFICATION rather than asserting it. A messy or legacy project is exactly where blind scanning produces a wrong context — be slower and more skeptical there.
When to use
Starting or formalizing a project agents will work on; refreshing or deepening context on an existing or messy project; whenever the user wants AGENTS.md / CLAUDE.md / README or an architecture baseline; or on /groundwork.
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.
- 8d ago First seen · 242 lines · 132 tokens per session scan A 62d9f08f33bb
groundwork is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 24d ago), licensed MIT. It adds 132 tokens to every session and 2,993 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…