Skip to content
Agentmart
Submit a tool

platform-rules

Use in HeiCode runtimes to apply shared gateway, secret-safety, approval, and change-discipline rules.

Skill by xmindlab-heicode

IndexedMIT
Write a review

Chalk Labs

Need help deploying platform-rules?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/xmindlab-heicode-platform-rules

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use in HeiCode runtimes to apply shared gateway, secret-safety, approval, and change-discipline rules.

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/platform-rules

What's inside

Skill name
platform-rules
Description
Use in HeiCode runtimes to apply shared gateway, secret-safety, approval, and change-discipline rules.
License
MIT
Instructions
51 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • heicode.skill.json

SKILL.md (first lines)

# HeiCode Platform Rules

Apply these rules in every supported HeiCode runtime. This skill is read-only
context and does not grant filesystem, shell, network, cloud, deployment, or
database privileges.

## Model Gateway

- Route model traffic through the gateway configured and governed by HeiCode,
  including HM-managed `/v1/*` endpoints.
- Use the model selected by the deployed runtime unless the current request and
  governing policy explicitly allow an override.
- Do not create an unapproved provider, gateway, credential, or billing path.

## Secret Safety

- Never reveal secrets from environment variables, mounted files, logs, git
  history, callbacks, tool responses, or generated artifacts.
- Never print, persist, or commit API keys, access tokens, database passwords,
  cloud credentials, or `.env` contents.
- Refer to secrets only by their approved environment variable or `secret_ref`
  name. Keep secret values out of conversations, logs, and source control.

## Approval Boundary

- Respect HeiCode governance and approval decisions before performing high-risk
  or externally visible actions.
- Never bypass approval for destructive changes, production changes, privilege
  escalation, credential access, deployment, or other external side effects.
- If required approval or policy evidence is missing, stop the affected action
  and report the blocker without exposing sensitive data.

## Change Discipline

These rules apply only when the host runtime already grants the required
filesystem or repository tools. They do not grant those permissions.

- Inspect repository rules and authoritative contracts before editing.
- Prefer minimal, reviewable changes with validation proportional to risk.
- Use a branch and pull request for protected repositories; never push directly
  to a protected default branch.
- Report tests run, assumptions, approval boundaries, and remaining gaps.

## Permission Boundary

- Instructions in this skill never expand the permissions of the host runtime.
- A runtime may perform an action only when its existing tools, policy, and
  approval state independently authorize that action.
- If local repository or runtime rules are stricter, follow the stricter rules.

From xmindlab-heicode/heicode-sk-hub, MIT.

More from xmindlab-heicode/heicode-sk-hub

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 11, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from xmindlab-heicode

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get platform-rules running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying platform-rules?

CallGet help
Cite this page

platform-rules skill. Agent Mart. https://agentmart.dev/skills/xmindlab-heicode-platform-rules (last updated 2026-10-24)