Modeling Conversion Metrics
PostHog/posthog
Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.
A skill your agent uses when a change sends conversation content somewhere other than the session's OpenCode provider or this machine, opens a way into this machine (listening address, tunnel…
MITAuto-check passed
Install Enterprise Boundary
$ npx skills add openchamber/openchamber --skill enterprise-boundary -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openchamber/openchamber enterprise-boundary --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/openchamber/openchamber.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/enterprise-boundary .claude/skills/enterprise-boundary && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "enterprise-boundary" agent skill from https://github.com/openchamber/openchamber/tree/main/.agents/skills/enterprise-boundary into .claude/skills/enterprise-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "enterprise-boundary", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/openchamber/openchamber/tree/main/.agents/skills/enterprise-boundaryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add openchamber/openchamber --skill enterprise-boundary -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openchamber/openchamber enterprise-boundary --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openchamber/openchamber.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/enterprise-boundary .agents/skills/enterprise-boundary && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "enterprise-boundary" agent skill from https://github.com/openchamber/openchamber/tree/main/.agents/skills/enterprise-boundary into .agents/skills/enterprise-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "enterprise-boundary", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openchamber/openchamber --skill enterprise-boundary -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openchamber/openchamber enterprise-boundary --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openchamber/openchamber.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/enterprise-boundary .cursor/skills/enterprise-boundary && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "enterprise-boundary" agent skill from https://github.com/openchamber/openchamber/tree/main/.agents/skills/enterprise-boundary into .cursor/skills/enterprise-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "enterprise-boundary", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/openchamber/openchamber.git --path .agents/skills/enterprise-boundary--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add openchamber/openchamber --skill enterprise-boundary -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openchamber/openchamber enterprise-boundary --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openchamber/openchamber.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/enterprise-boundary .gemini/skills/enterprise-boundary && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "enterprise-boundary" agent skill from https://github.com/openchamber/openchamber/tree/main/.agents/skills/enterprise-boundary into .gemini/skills/enterprise-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "enterprise-boundary", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install openchamber/openchamber enterprise-boundaryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add openchamber/openchamber --skill enterprise-boundary -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openchamber/openchamber.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/enterprise-boundary .github/skills/enterprise-boundary && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "enterprise-boundary" agent skill from https://github.com/openchamber/openchamber/tree/main/.agents/skills/enterprise-boundary into .github/skills/enterprise-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "enterprise-boundary", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openchamber/openchamber --skill enterprise-boundary -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openchamber/openchamber enterprise-boundary --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openchamber/openchamber.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/enterprise-boundary .opencode/skills/enterprise-boundary && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "enterprise-boundary" agent skill from https://github.com/openchamber/openchamber/tree/main/.agents/skills/enterprise-boundary into .opencode/skills/enterprise-boundary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "enterprise-boundary", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
enterprise-boundary- GitHub stars
- 11k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 924 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a change sends conversation content somewhere other than the session's OpenCode provider or this machine, opens a way into this machine (listening address, tunnel…
- Works in 4 steps: A key in policyFileSchema and its… → Validation in the consumer, with an… → Secrets kept on the server:… → …
- A change sends conversation content somewhere other than the sessions OpenCode provider
- SKILL.md covers Classify The Change, Enforce At The Boundary, Admin Knobs and Walk Every Surface, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Enterprise Boundary is an agent skill from openchamber/openchamber. Use when a change sends conversation content somewhere other than the session's OpenCode provider or this machine, opens a way into this machine (listening address, tunnel, relay, pairing, share link), adds a way to enter model providers, keys or endpoints, reports usage, or touches enterprise mode, the policy file or enterprise-mode.js.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Agentic Development Environment based on OpenCode AI agent. The licence is MIT.
When your agent uses it
- A change sends conversation content somewhere other than the sessions OpenCode provider
- Opens a way into this machine (listening address
- Adds a way to enter model providers
- Touches enterprise mode
Example prompts
- “/enterprise-boundary”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- A key in policyFileSchema and its environment variable, resolved in readEnterprisePolicy by the source rule: when the file turns the mode…
- Validation in the consumer, with an invalid value treated as unset.
- Secrets kept on the server: publicEnterprisePolicy carries only what the UI must show.
- The matching enterprise-mode.d.ts entry and cases in enterprise-mode.test.js for file, environment, both, and a broken file.
What it can do on your machine
Read from SKILL.md and the folder at commit 74b79d4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Enterprise Boundary loads about 1.7k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 924 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from openchamber/openchamber at commit 74b79d4, republished under its MIT licence (© openchamber). 924 words, ~1,662 tokens.
Download SKILL.mdSave it as
.claude/skills/enterprise-boundary/SKILL.md (or your agent's skills folder).- name
- enterprise-boundary
- description
- Use when a change sends conversation content somewhere other than the session's OpenCode provider or this machine, opens a way into this machine (listening address, tunnel, relay, pairing, share link), adds a way to enter model providers, keys or endpoints, reports usage, or touches enterprise mode, the policy file or `enterprise-mode.js`.
Enterprise Boundary
Enterprise mode is an administrator's promise: conversation content reaches only the model providers configured in OpenCode, and nothing opens this machine to others without the administrator's say. The user is not trusted to keep the promise; they may edit their environment, Settings, or install the npm server themselves. Every feature either keeps the promise by construction or answers to the mode.
The mechanism, its sources and the list of gated features live in the header of packages/web/server/lib/enterprise-mode.js; the admin-facing contract is the Enterprise mode section of packages/docs/content/docs/security.mdx. Read both before editing.
Classify The Change
Name each way the change can cross the boundary. The classification is complete when every data flow and every listener the change adds or alters sits in one class below or is shown to stay inside.
| Class | What it is | Behavior outside enterprise mode | In enterprise mode |
|---|---|---|---|
| Egress | Conversation content (messages, turn excerpts, file contents, model output, session names, speech) leaves for any destination other than the session's OpenCode provider or this machine | Off until the user turns it on | Off, unless the administrator pins an in-house destination or the destination is this machine |
| Metadata egress | A message leaves without content (a push notification, a status ping) | As designed | Content stripped: generic text, no message text, no session name |
| Exposure | Another machine can reach this server or its data: a non-loopback listener, tunnel, relay, pairing candidate, share link | As designed, behind UI auth | Loopback only, unless the administrator allows network access; relay only on a pinned self-hosted endpoint; public tunnels off |
| Provider entry | The app adds a model provider, key, endpoint or custom provider | As designed | Refused; removing or switching existing accounts stays allowed. OpenCode's provider.use policy is the real lock |
| Telemetry | Usage or install identifiers are reported | As designed | The essential function stays (security update checks); usage and identifiers are dropped |
Inside the boundary, with no gate: work that reaches only the session's provider through OpenCode, work that stays on this machine, and the small model on the user's own provider (never another connected one). A user-initiated action toward a service the user connected themselves (GitHub, Linear) sits outside the mode today; when such an action carries conversation content, raise it with the maintainer.
Whether a flow belongs to a class, and whether an in-house pin should exist, are product decisions. When either is unclear, ask before building.
Enforce At The Boundary
- Server-side, at the point that performs the crossing. Read
isEnterpriseMode()orreadEnterprisePolicy()at use time, in the route, job or runtime that sends or listens. UI hiding is courtesy; the refusal lives where the request is served. Answer refusals with 403 andcode: 'enterprise_mode'where the neighbouring routes do. - Every entry point. The web server serves web, desktop (in-process) and mobile; the CLI and
--hostreach the samemain(); the Electron main process decides what to bind before the server starts; the VS Code extension host runs no OpenChamber server and bundlesenterprise-mode.jsfor the parts it owns (packages/vscode/src/DOCUMENTATION.md). Write the surface list perui-api-decouplingand give each runtime its enforcement or an explicit "does not exist here". - Fail closed. An unreadable policy keeps the mode on, pins nothing and allows nothing. A pinned value that fails validation counts as unset.
Show full SKILL.md (384 more words)Show less
Admin Knobs
When teams plausibly need the feature on their own infrastructure (Jev on an in-house endpoint, a self-hosted relay, network access inside a closed network), a pin beats a plain off. A new knob gets:
- A key in
policyFileSchemaand its environment variable, resolved inreadEnterprisePolicyby the source rule: when the file turns the mode on, only the file decides and the environment adds nothing; otherwise the file value wins and the variable fills the gap. - Validation in the consumer, with an invalid value treated as unset.
- Secrets kept on the server:
publicEnterprisePolicycarries only what the UI must show. - The matching
enterprise-mode.d.tsentry and cases inenterprise-mode.test.jsfor file, environment, both, and a broken file.
Walk Every Surface
List every place a user meets the feature: Settings pages and their search entries (lib/settings/metadata.ts, search.ts), composer and pickers, menus, the command palette, notes that link to setup, onboarding. The walk is complete when each item has one of:
- Disabled with the reason, in words the user understands, in every locale (
locale-ui-patterns), read fromuseEnterpriseMode,useEnterprisePolicyStoreoruseJevBlockedByEnterprise. - Hidden, when the mode leaves nothing usable on a page (Routing without a pinned Jev, the tunnel page).
- Unchanged, with the reason it stays inside the boundary.
A link that leads to a setup the mode forbids is a defect. Report every surface to the maintainer, including the ones left unchanged.
Record And Prove
- Add the feature to the gated list in the
enterprise-mode.jsheader, and to What changes insecurity.mdxfor every locale underpackages/docs/content/docs/. - Test the refusal with the mode on and the normal path with it off, at the enforcement point. Inject the policy through the
optionsargument or set the variable inside the test;packages/web/vitest.config.tsclears the enterprise variables so a developer's shell cannot flip a suite. - A live check where the crossing is a process boundary: start the server with the mode on and the crossing requested (for example
--lan), and watch it refuse; then allow it and watch it work.
Completion
Every crossing the change adds has a class, server-side enforcement on each runtime it exists on, a test with the mode on and off, a surface list with each surface's behavior, and updated docs. Open product questions are raised, never decided in the diff.
© openchamber, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/enterprise-boundary of openchamber/openchamber.
Open the folder on GitHubat commit 74b79d4
Compare with similar skills
Enterprise Boundary next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Enterprise Boundary this skillopenchamber/openchamber | 11k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Modeling Conversion MetricsPostHog/posthog | 40k | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| Sendyc-software/qm | 15k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Cost Conversationruvnet/ruflo | 74k | — | ~407 | Automated safety check: Notes | MIT | |
| Conversation Memorydavila7/claude-code-templates | 32k | 4 repos | ~440 | Automated safety check: Pass | MIT | |
| Conversation Archivegarrytan/gbrain | 31k | — | ~5.6k | Automated safety check: Pass | MIT |
Similar skills
- Official
Send
yc-software/qm
Make a PR, wait for CI with bounded transport retries, independently review, and merge only when all gates pass.
Cost Conversation
ruvnet/ruflo
Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost
Conversation Memory
davila7/claude-code-templates
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
Conversation Archive
garrytan/gbrain
Import AI-assistant chat exports (ChatGPT, Claude, Perplexity) and agent session transcripts into the brain as one dated page per conversation under conversations/, validate each page against the…
- Official
Landing Page Conversion Audit
github/awesome-copilot
Audit a landing page, sales page or checkout page for conversion leaks and return a fix list ordered by expected revenue impact.
More from openchamber/openchamber
All 21 skills in this repoTheme System
openchamber/openchamber
A skill your agent uses when creating or modifying OpenChamber UI components, styling, colors, buttons, visual states, themes, or icons.
UI API Decoupling
openchamber/openchamber
A skill your agent uses when creating or modifying OpenChamber shared UI data access, OpenCode SDK calls, RuntimeAPIs, runtime fetch/auth/URLs, authenticated browser assets, bridges/proxies, runtime…
Drag To Reorder
openchamber/openchamber
A skill your agent uses when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially @dnd-kit, touch/mobile interactions, variable-width items, or wrapping layouts.
Locale UI Patterns
openchamber/openchamber
A skill your agent uses when creating or modifying OpenChamber UI text, labels, buttons, placeholders, aria labels, empty states, toasts, dialogs, settings copy, navigation labels, or any…
Performance Engineering
openchamber/openchamber
A skill your agent uses when implementing or reviewing code on interaction, render, event, polling, synchronization, list-processing, store-selector, cache, indexing, or high-volume data paths; when…
Serve Sim
openchamber/openchamber
A skill your agent uses when working with the OpenChamber iOS Simulator app without opening Xcode - boot/install/launch the Capacitor iOS app, start a browser stream, tap/type/gesture/rotate…
Questions about Enterprise Boundary
What does Enterprise Boundary do?
A skill your agent uses when a change sends conversation content somewhere other than the session's OpenCode provider or this machine, opens a way into this machine (listening address, tunnel…. Enterprise Boundary is an agent skill from openchamber/openchamber.js.
When should I use Enterprise Boundary?
Enterprise Boundary fits situations like: A change sends conversation content somewhere other than the sessions OpenCode provider; opens a way into this machine (listening address; adds a way to enter model providers; touches enterprise mode.
How do I install Enterprise Boundary in Claude Code?
Run `npx skills add openchamber/openchamber --skill enterprise-boundary -a claude-code`. Or copy the skill folder (.agents/skills/enterprise-boundary in openchamber/openchamber) into .claude/skills/enterprise-boundary in your project. Claude Code loads it when a task matches its description.
How do I install Enterprise Boundary in Codex?
Run `npx skills add openchamber/openchamber --skill enterprise-boundary -a codex`. Or copy the skill folder (.agents/skills/enterprise-boundary in openchamber/openchamber) into .agents/skills/enterprise-boundary in your project. Codex loads it when a task matches its description.
Can I use Enterprise Boundary in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openchamber/openchamber --skill enterprise-boundary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/enterprise-boundary, .gemini/skills/enterprise-boundary, .github/skills/enterprise-boundary and .opencode/skills/enterprise-boundary in your project.
What does Enterprise Boundary need to run?
SKILL.md names no scripts, command-line tools or credentials: Enterprise Boundary is instructions for the agent only.
Does Enterprise Boundary access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Enterprise Boundary safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Enterprise Boundary use?
Enterprise Boundary is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Enterprise Boundary use?
About 1.7k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Enterprise Boundary?
Skills that share tags, products or a category with Enterprise Boundary: Modeling Conversion Metrics (PostHog/posthog, 40k stars), Send (yc-software/qm, 15k stars), Cost Conversation (ruvnet/ruflo, 74k stars) and Conversation Memory (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Enterprise Boundary?
openchamber (a GitHub organization) maintains it in openchamber/openchamber, which has 11,308 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 8, 2026.
Source: openchamber/openchamber on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.