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.
git clone --depth 1 https://github.com/nitinjain999/platform-skillsWrote 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.
[](https://agentmods.dev/commands/nitinjain999/platform-skills/opa)<a href="https://agentmods.dev/commands/nitinjain999/platform-skills/opa"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/opa.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.01969 |
| Opus 5 | $0.00049 | $0.00984 |
| Sonnet 5 | $0.00020 | $0.00394 |
| Haiku 4.5 | $0.00010 | $0.00197 |
Grade A, and why
opa 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write, test, validate, explain, and debug OPA Rego policies with Conftest.
AI-agent behavior, not infra policy: to gate what an AI coding agent (Copilot, Claude Code) can edit or run in a repo, use
/platform-skills:ai-governance— a different policy engine for a different input shape (tool calls and diffs, not Terraform/Kubernetes manifests).
Interactive Wizard (fires when no arguments are provided)
When invoked with no arguments, ask before proceeding:
Q1 — Mode?
What do you need?
1. generate — write a new production-ready Rego policy
2. test — write _test.rego unit tests for an existing policy
3. validate — run the full pipeline (fmt, lint, tests) against a directory
4. explain — translate an existing Rego policy into plain English
5. debug — diagnose why a policy is not firing as expected
Enter 1–5 or mode name:
Q2 — Context (after mode selected, one at a time):
- generate:
Describe the policy — target resource type (Terraform/Kubernetes/GHA/Dockerfile) and what to deny or warn on: - test:
Paste the Rego policy to write tests for: - validate:
Provide the directory path containing your .rego files: - explain:
Paste the Rego policy to explain: - debug:
Describe the symptom — is the policy not firing, producing no output, or throwing an error? Paste the conftest output:
Then proceed into the relevant mode below.
Mode: generate
Write a production-ready Rego policy from a description.
Steps:
- Ask for: target resource type (Terraform HCL, Kubernetes manifest, GitHub Actions workflow, Dockerfile, JSON/YAML), the rule logic (what to deny or warn on), and whether a named namespace is needed
- Parse what Conftest sees — use
conftest parse <file>to show the input shape if the user has a file, then write rules that match that shape exactly - Generate the policy file:
- Start with a
# METADATAblock:title,description,authors,entrypoint: true - Declare
package <namespace>— usemainonly when a single policy set applies; use a named package (package terraform.iam,package k8s.pods) for multi-domain repos - Add
import rego.v1— required for modern Rego syntax - Use
denyfor hard failures,warnfor advisory violations,violationfor OPA framework integrations (Gatekeeper, Conftest policy sets) - Generate a descriptive
msgthat includes the offending resource name/value and a remediation hint - Use
somefor iteration,infor membership,startswith/containsfor string matching
- Start with a
- Show the Conftest command to test the policy against sample input
- State CI placement: conftest runs after
terraform validateand beforeterraform planas a blocking gate — failing conftest must prevent plan from running
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.
- 7d ago First seen · 142 lines · 98 tokens per session scan A 9bb1413548f3
opa is a command published in the GitHub repository nitinjain999/platform-skills (41 stars, last pushed 5d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,969 once invoked, about $0.0005 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.
Other commands, from other repositories
conjure-config
Set, view, or remove conjure preferences. Asks questions to understand what you want, then writes plain-language instructions that conjure commands follow automatically.
conjure-agent
Creates or updates a Claude Code agent definition (/.claude/agents/ .md or project-local).
conjure
Use when you want to build a new Claude Code skill, agent, hook, or MCP server but aren't sure which — or when you want to describe what you want in plain language. Auto-detects the right artifact type, asks targeted questions, explains the reasoning, then builds it.
conjure-mcp
Create a Claude Code MCP (Model Context Protocol) server. Provide a description of what external system or data source you want Claude to connect to.
conjure-help
Show help for the conjure toolkit — all commands, argument syntax, update modes, and decision guide. Use when you want to know which conjure command to use or how any conjure command works.
setup
Run SetupGuide interactively. Without arguments, walks through every incomplete setup step in sequence until all are done or the user exits. With a named argument, configures that specific MCP. Type "skip" to skip the current step, "exit" or "done" to stop setup at any point.