Solution

# Each laptop has different agent rules. *Set them once, and see every change.*

Write skills, instructions and Protect rules once, and both agents get them on every machine. On Team, one Protect policy covers every member, and History shows who changed a rule and why.

[Talk to us](mailto:sales@context-mode.com) [Get started free](https://console.context-mode.com/login)

Pick a moment

Plain words Just a question House rules Push to main Team policy Who changed it

“Our blog URLs end with a dash and the tests are red. Fix it.”

Your skills *diagnosing-bugs* *to-tickets*

Nobody typed a skill name. The skill that matches loads, and the reply names it.

“Walk me through how slugify turns a title into a slug.”

Your skills *diagnosing-bugs* *to-tickets*

A question about the code loads no skill. At most one skill loads per turn.

You write the rules once.

Before

- A rules file in each repo
- A different file for each agent

After

- One text in Settings
- Both agents, every machine

Every request from both agents on your account carries it, on every machine. A message in the turn still wins.

An agent tries “git push origin main”.

Blocked · never reaches your shell **Push to protected branches**

Protected branches change through reviewed pull requests.

With Protect on, the agent reads the rule and why, and offers a branch and a pull request.

On Team, one Protect policy covers every member.

```
Read environment files · Block
Push to protected branches · Block
Change cloud resources · Monitor
```

Set by the org. Every member's agents follow it, on every machine.

A rule got looser. Who did it, and why?

Each History entry *The time* *Who: a person or an API key* *How: editor, import, preset or pack* *The rule before and after* *The reason* *Loosens the policy*

An API key can only tighten the policy. Each entry's hash covers the one before, so an edit breaks the chain.

The problem

## Six engineers, six setups. *Six sets of rules.*

**Skills live on each disk**

Each agent loads skills from files on the local disk. Unless IT ships them with managed settings, every change must reach each laptop.

**Rules differ per repo and per agent**

CLAUDE.md for one agent, AGENTS.md for the other, in each repo. One engineer's agent follows the house rules. Another's never saw them.

**No record of a change**

A rule gets looser and the agent runs a call it should not. Nobody can say who changed the rule, when or why.

How it works

## Standards on the gateway. *Every request carries them.*

1. 01 **Import your skills** Paste a GitHub repo URL in the console. Preview the skills, then add one or all.
2. 02 **Write the rules once** Instructions in Settings, and Protect rules for tool calls. No file to copy into each repo.
3. 03 **Each request gets them** The gateway adds the skill that matches and your instructions. Once you turn Protect on, it checks each tool call with the rules you pick, before the shell sees it.

**Your agents**

Claude Code and Codex, on any laptop, send each request to the gateway.

**Context Mode**

Adds the skill that matches and your instructions. Checks tool calls with your Protect rules.

**Your model account**

Your own Anthropic or OpenAI account gets the request and pays the model.

Proof

## The rule, said out loud. *Every change on record.*

**10 of 10** right skill choices on the 10 texts where the old and new judge disagreed, against 4 of 10 for the old judge

**Hash chain** each History entry covers the one before, so an edited or deleted entry breaks the chain

**Keys only tighten** a change that loosens the policy needs a person signed in and a reason

```
Blocked by your team’s policy: Push to protected branches. Protected branches change through reviewed pull requests.
```

The refusal the agent reads when it tries to push to main, from a real turn through the gateway. Skill choices: an offline eval on recorded turns, small sample, judged by one person. Treat it as direction, not as live accuracy. [Skill eval →](https://context-mode.com/blog/the-right-skill-at-the-right-time) [History docs →](https://context-mode.com/docs/protect#history)

Compared

## Where your standards live. *One place for both agents.*

|  | Context Mode | Built into each agent |
| --- | --- | --- |
| Skills | One catalog per account, for both agents | SKILL.md files per agent; managed settings deploy them |
| Which skill loads | The one that matches, named in the reply | The agent decides |
| Instructions | One text per account, for both agents | Files in each repo, the home folder or managed by IT |
| Tool-call rules | One Protect policy for both agents; on Team, for every member | Per agent, through permissions and managed settings |

Where they are stronger: managed settings and plugin marketplaces reach every machine in an org, and a user cannot switch them off. Skills have no team roles yet. [Method and sources →](https://context-mode.com/docs/landscape)

Team

## One policy *for the whole org.*

**One Protect policy, every member**

On Team, one Protect policy covers every member of the org. Every member's agents follow it, on every machine.

**Every change on record**

History shows who changed a rule, how and why. Loosening changes are marked.

**Watch first**

Put a rule in Monitor. The call runs and the log records "would block".

[Talk to us](mailto:sales@context-mode.com) [See plans](https://context-mode.com/pricing)

Products used

## What this *uses.*

**[Skills](https://context-mode.com/skills)**

Import from GitHub once. The skill that matches loads, one per turn at most. [Skills docs](https://context-mode.com/docs/skills).

**[Instructions](https://context-mode.com/instructions)**

Rules you write once, in Settings, 4,096 characters at most. Every request carries them. [Docs](https://context-mode.com/docs/instructions).

**[Protect](https://context-mode.com/protect)**

Checks each tool call before it runs, once you turn it on. On Team, one policy for the org. [Docs](https://context-mode.com/docs/protect).

Related: [Share skills](https://context-mode.com/use-cases/share-skills) to import your team's skill repo · [Platform teams](https://context-mode.com/solutions/platform-teams) for roll-out · [Shared context](https://context-mode.com/solutions/shared-context) for facts every agent knows

## Set your standards once. *See every change.*

*npx @context-mode/cli* connects your agents. 1,000 requests free, no card. Your own Anthropic or OpenAI account pays the model. We add no fee on tokens.

[Get started free →](https://console.context-mode.com/login) [Talk to us about Team →](mailto:sales@context-mode.com)