Create Policy

What it does

When your agent uses it

• Asked to create
• Explain an OPA policy
• Governance policy
• Compliance rule

Example prompts

• “/create-policy”

Requirements

• Compatibility (from SKILL.md): Requires Harness MCP v2 server (harness-mcp-v2)

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1Identify Policy Requirements
2. 2Create the Policy
3. 3Verify Compliance Results

What it can do on your machine

Read from SKILL.md and the folder at commit c25faee. 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 (its code samples are rego).

  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.

• Compatibility

  Requires Harness MCP v2 server (harness-mcp-v2)

  From compatibility in the SKILL.md frontmatter.

Context cost

Create Policy loads about 1.9k tokens when it runs, and up to ~43k if it reads all its reference files. Until then it costs about 151 tokens; SKILL.md has 636 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~151

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~43k

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

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 harness/harness-skills at commit c25faee, republished under its Apache-2.0 licence (© harness). 636 words, ~1,948 tokens.

name

create-policy

description

Create OPA governance policies for Harness via MCP. Define policies that enforce compliance rules on pipelines, services, environments, feature flags, artifacts, code repositories, templates, SBOM, security tests, Terraform, GitOps, connectors, secrets, and more. Use when asked to create, write, fix, or explain an OPA policy, Rego rule, deny rule, governance policy, compliance rule, or policy-as-code for any Harness entity. Trigger phrases: create policy, OPA policy, governance policy, compliance rule, rego policy, deny rule, enforce policy, security policy, supply chain governance.

compatibility

Requires Harness MCP v2 server (harness-mcp-v2)

metadata.author

Harness

metadata.version

1.0.0

metadata.mcp-server

harness-mcp-v2

license

Apache-2.0

Call MCP tool: harness_create
Parameters:
  resource_type: "policy"
  org_id: "<organization>"
  project_id: "<project>"
  body: <policy definition>

Call MCP tool: harness_list
Parameters:
  resource_type: "scs_compliance_result"
  org_id: "<organization>"
  project_id: "<project>"

package harness.artifact

deny[msg] {
  not input.artifact.sbom
  msg := "Artifact must have an SBOM before deployment"
}

package harness.artifact

deny[msg] {
  vuln := input.artifact.vulnerabilities[_]
  vuln.severity == "CRITICAL"
  msg := sprintf("Critical vulnerability %s found in artifact", [vuln.cve_id])
}

package harness.artifact

approved_bases := {"alpine", "distroless", "ubuntu"}

deny[msg] {
  not approved_bases[input.artifact.base_image]
  msg := sprintf("Base image '%s' is not in the approved list", [input.artifact.base_image])
}

package harness.artifact

deny[msg] {
  not input.artifact.signed
  msg := "Artifact must be signed before deployment"
}

© harness, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 18 other files (references) in skills/create-policy of harness/harness-skills.

• SKILL.md
• references/advanced-patterns.md
• references/entity-code-repository.md
• references/entity-connector.md
• references/entity-database.md
• references/entity-feature-flag.md
• references/entity-gitops.md
• references/entity-override.md
• references/entity-pipeline.md
• references/entity-sbom.md
• references/entity-secret.md
• references/entity-security-tests.md
• references/entity-service-env-infra.md
• references/entity-template.md
• references/entity-terraform.md
• references/entity-upstream-firewall.md
• references/entity-variable.md
• references/quality-tests.md
• references/rego-writing-guide.md

Open the folder on GitHubat commit c25faee