Common Ground Agent Skill

Establish and maintain enough shared understanding for ambiguous project work.

Context cost
2.6k tokensestimated from the bundle, loaded when it triggers
Bundle
3 files · 10.4 kBtext throughout, nothing executable
Licence
Apache-2.0the author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Establish and maintain enough shared understanding for ambiguous project work. Use when user intent, terminology, acceptance criteria, tacit preferences, or consequential assumptions may differ; after a misunderstanding; or before long-running work whose deviations would be expensive. Do not use for trivial mechanical tasks with clear, verifiable outcomes.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md8.2 kB · preview
--- name: common-ground license: Apache-2.0 ---
7# Common Ground
8
9Reach a **grounding criterion**: the user and agent mutually understand the work well enough for its current purpose, with the least necessary joint effort. Do not try to eliminate all uncertainty. Prevent material gaps from being decided silently.
10
11The prompt, plan, and current beliefs are the **map**. The codebase, runtime, real constraints, and the user's reactions are the **territory**. Treat the four kinds of unknowns as a scan for gaps, not as four phases or four questionnaires.
12
13## Invariants
14
15- Ground before asking. Inspect relevant source, docs, tests, config, current behavior, and prior decisions before requesting information the environment can supply.
16- The user owns intent, trade-offs, and acceptable outcomes. Evidence owns facts. The agent may recommend a default, but must not present an inferred preference as settled.
17- Keep evidence-backed facts, user-confirmed decisions, agent assumptions, and unresolved unknowns visibly distinct.
18- A gap is **material** when a plausible answer could change the goal, scope, domain meaning, user-visible behavior, public contract, data, security, permissions, external effects, a hard-to-reverse choice, or substantial work that verification would not cheaply catch. Material gaps require a user decision or explicit acceptance of the risk; other gaps need not block.
19- Silence is not confirmation of a material user-owned choice.
20- Alignment is continuous. Planning cannot exhaust unknown unknowns, so re-ground when the territory contradicts the map.
21- An alignment-only request does not authorize implementation or external mutation.
22
23## The Common Ground Loop
24
25### 1. Ground the current map
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,259 words
Files3
LicenceApache-2.0
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈100
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
2,500
on trigger
The instruction body and 2 supporting files, read only when the skill fires.
1.3%
of a 200k window
Ten skills this size would take about 13% of the window before you open a file.
050k100k150k200k context window

2.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

3 files, 10.4 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md8.2 kB
  • agents/openai.yaml0.3 kB
  • references/alignment-record.md1.9 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 3 files you can review in full before installing. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Common Ground · 2.6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/common-ground/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/common-ground" ] && { [ ! -e .claude/skills/common-ground ] || { mv .claude/skills/common-ground "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/common-ground" .claude/skills/ && echo "Installed .claude/skills/common-ground"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add hughlee824/common-ground

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/common-ground/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/common-ground/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/common-ground" ] && { [ ! -e ~/.claude/skills/common-ground ] || { mv ~/.claude/skills/common-ground "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/common-ground" ~/.claude/skills/ && echo "Installed ~/.claude/skills/common-ground" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/common-ground/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencehughlee824/common-ground

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

HU
HughLee824

Publishes on mcprush.

0 servers listed2 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill