create-policy

create-policy is a skill for Claude Code, Codex from harness/harness-skills. It costs 126 tokens per session (1,717 once invoked), scanned A, original, Apache-2.0.

A tool for creating OPA governance policies in Harness, a platform for automating software delivery. These policies define rules for items such as pipelines, services, repositories, secrets, and security checks.

In plain words
What is it for?
Use it to write, fix, explain, and create policies that warn or block actions when defined conditions are met.
Why use it?
It helps teams enforce compliance rules consistently instead of checking every deployment or configuration by hand.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to write, fix, explain, and create policies that warn or block actions when defined conditions are met.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/harness/harness-skills/create-policy
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add harness/harness-skills --skill create-policy
Clone the repo
git clone --depth 1 https://github.com/harness/harness-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for create-policy

README.md
[![agentmods](https://agentmods.dev/badge/skills/harness/harness-skills/create-policy/github.svg)](https://agentmods.dev/skills/harness/harness-skills/create-policy)
Your own site
<a href="https://agentmods.dev/skills/harness/harness-skills/create-policy"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/create-policy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for create-policy

Your own site · 80×15
<a href="https://agentmods.dev/skills/harness/harness-skills/create-policy"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/create-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 142
    Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.
    Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.01717
Opus 5 $0.00063 $0.00859
Sonnet 5 $0.00025 $0.00343
Haiku 4.5 $0.00013 $0.00172

Measured 9d ago against content hash 3f0481f7def4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

create-policy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/create-policy/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Policy

Create OPA governance policies for Harness Software Supply Chain Assurance (SCS) via MCP.

Instructions

Step 1: Identify Policy Requirements

Determine what the policy should enforce:

  • What entity type is the policy targeting? (pipeline, service, environment, feature flag, etc.)
  • What is the enforcement action (warn, deny)?
  • What scope should the policy apply to?
  • What action triggers the policy? (onrun, onsave, onstep, etc.)

For writing Rego policies, consult references/rego-writing-guide.md for the complete Rego writing rules, entity types, package names, and common patterns. For entity-specific schemas and examples, see the entity reference files listed in that guide.

Step 2: Create the Policy

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

OPA policies are managed under the governance toolset — resource_type: "policy" supports full CRUD (list, get, create, update, delete).

Step 3: Verify Compliance Results

After a policy is created, check compliance status on artifacts or repositories:

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

Common Policy Patterns

Require SBOM Generation

Enforce that all artifacts have an SBOM before deployment:

package harness.artifact

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

Block Critical Vulnerabilities

Deny deployment of artifacts with critical CVEs:

package harness.artifact

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

Enforce Approved Base Images

Restrict container images to approved base images:

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])
}

Read the full file on GitHub · 185 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 185 lines · 126 tokens per session scan A 3f0481f7def4

Subscribe to this mod's changes

create-policy is a skill published in the GitHub repository harness/harness-skills (105 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 126 tokens to every session and 1,717 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories