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.
npx skills add MingyiSecLab/Mingyi-Atlas --skill opplan-convertergit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/opplan-converter)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/opplan-converter"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/opplan-converter/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/mingyiseclab/mingyi-atlas/opplan-converter"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/opplan-converter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.00891 |
| Opus 5 | $0.00016 | $0.00445 |
| Sonnet 5 | $0.00006 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
opplan-converter 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OPPLAN Converter — CONOPS to Ralph Loop Format
The OPPLAN is the direct analogue of ralph's prd.json — it's the file the autonomous loop reads each iteration to decide what to do next. Each objective must be completable by one agent in one context window.
When to Use
- After both
roe.jsonandconops.jsonexist - User wants to convert planning docs into executable tasks
- Starting the autonomous red team loop
Prerequisites
Read both roe.json and conops.json first. The RoE constrains what's allowed; the CONOPS defines the kill chain and threat profile.
See ../references/schema-quick-reference.md for the OPPLAN and Objective schema fields, valid status values, and enum types.
Workflow
Step 1: Extract Kill Chain from CONOPS
Read the CONOPS kill chain phases. Only create objectives for authorized phases.
Step 2: Decompose into Objectives
Each objective must follow the one context window rule — if an agent can't complete it in a single session, it's too big. Split it.
See references/objective-templates.md for recon-phase templates and references/objective-rules.md for the complete decomposition rules.
ID Convention: OBJ-{NUMBER} (auto-generated as OBJ-001, OBJ-002, ...)
Phase → Sub-Agent Routing:
| Phase | Sub-Agent | MITRE Tactics |
|---|---|---|
| recon | recon | TA0043 Reconnaissance |
| initial-access | exploit | TA0001 Initial Access, TA0002 Execution |
| post-exploit | postexploit | TA0003-TA0009 (Persistence thru Collection) |
| c2 | postexploit | TA0011 Command and Control |
| exfiltration | postexploit | TA0010 Exfiltration |
Step 3: Write Acceptance Criteria
Every objective MUST have three mandatory criteria types:
- Scope check — "All targets verified against roe.json in-scope list"
- OPSEC check — At least one OPSEC-related criterion (rate limit, timing, etc.)
- Output persistence — "Results saved to /recon/..." (or exploit/, post-exploit/) with specific file path
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 84 lines · 32 tokens per session scan A 5d5efc97cd4b
opplan-converter is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 891 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.