Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pr-pm/prpmnpx agentmods add skills/pr-pm/prpm/adding-new-ai-formatWrote 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/skills/pr-pm/prpm/adding-new-ai-format)<a href="https://agentmods.dev/skills/pr-pm/prpm/adding-new-ai-format"><img src="https://agentmods.dev/badge/skills/pr-pm/prpm/adding-new-ai-format/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.
<a href="https://agentmods.dev/skills/pr-pm/prpm/adding-new-ai-format"><img src="https://agentmods.dev/badge/skills/pr-pm/prpm/adding-new-ai-format.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.06795 |
| Opus 5.5 | $0.00014 | $0.02718 |
| Sonnet 5.5 | $0.00007 | $0.01359 |
| Haiku 4.5 | $0.00004 | $0.00679 |
Grade A, and why
adding-new-ai-format 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 2mo 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 — 942 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a New AI Format to PRPM
Complete process for adding support for a new AI editor format (like OpenCode, Cursor, Claude, etc.) to PRPM.
Overview
This skill documents the systematic process for adding a new AI format to PRPM, based on the OpenCode integration. Follow these steps in order to ensure complete integration across all packages.
Prerequisites
- Format documentation (understand file structure, frontmatter, directory conventions)
- Example files from the format
- Understanding of format-specific features (tools, agents, commands, etc.)
Step 1: Types Package (packages/types/)
File: src/package.ts
Add the format to the Format type and FORMATS array:
export type Format =
| 'cursor'
| 'claude'
| 'continue'
| 'windsurf'
| 'copilot'
| 'kiro'
| 'agents.md'
| 'gemini.md'
| 'claude.md'
| 'gemini'
| 'opencode' // Add new format here
| 'ruler'
| 'generic'
| 'mcp';
export const FORMATS: readonly Format[] = [
'cursor',
'claude',
// ... other formats
'opencode', // Add here too
'ruler',
'generic',
'mcp',
] as const;
Build and verify:
npm run build --workspace=@pr-pm/types
Step 2: Converters Package - Schema (packages/converters/schemas/)
Create JSON schema file: {format}.schema.json
Example structure:
{
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://registry.prpm.dev/api/v1/schemas/opencode.json",
"title": "OpenCode Agent Format",
"description": "JSON Schema for OpenCode Agents",
"type": "object",
"required": ["frontmatter", "content"],
"properties": {
"frontmatter": {
"type": "object",
"required": ["description"],
"properties": {
"description": { "type": "string" },
// Format-specific fields
},
"additionalProperties": false
},
"content": {
"type": "string",
"description": "Body content as markdown"
}
}
}
CRITICAL Schema Requirements:
$idmust use new URL pattern:https://registry.prpm.dev/api/v1/schemas/{format}.jsonfor base schemas- For subtypes:
https://registry.prpm.dev/api/v1/schemas/{format}/{subtype}.json - Add
"additionalProperties": falseto frontmatter object to catch invalid fields - String fields requiring slugs (like
name) should use pattern:"pattern": "^[a-z0-9-]+$"
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.
- 2mo ago First seen · 942 lines · 36 tokens per session scan A e455b7a2d2cd
adding-new-ai-format is a skill published in the GitHub repository pr-pm/prpm (124 stars, last pushed 25d ago), licensed MIT. It adds 36 tokens to every session and 6,795 once invoked, about $0.0001 per session on Opus 5.5. 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.
adding-new-ai-format compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adding-new-ai-formatpr-pm/prpm | Skill | 124 | 25d ago | MIT | A | 36 | Claude Code |
| best-practicesMoizIbnYousaf/Ai-Agent-Skills | Skill | 1.2k | 1mo ago | MIT | A | 35 | Claude Code, Codex |
| testing-for-system-prompt-leakageadriannoes/awesome-agentic-ai | Skill | 96 | 6d ago | MIT | A | 21 | Claude Code, Codex |
| red-teaming-llms-with-garakadriannoes/awesome-agentic-ai | Skill | 96 | 6d ago | MIT | B | 49 | Claude Code, Codex |
| llm-prompt-optimizertmolavi/mcp-agent-skills-hub | Skill | 9 | 1mo ago | MIT | A | 35 | Claude Code, Codex |
| openrouternateslabach/skills | Skill | 6 | 1mo ago | MIT | A | 60 | Claude Code, Codex |
| prompt-pilotsavasturkoglu1/promptpilot-plugin | Skill | 3 | 1mo ago | MIT | A | 63 | Claude Code, Codex |