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 agentmods add skills/openhands/extensions/mainframe-planningnpx skills add OpenHands/extensions --skill mainframe-planninggit clone --depth 1 https://github.com/OpenHands/extensionsWhat 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 | $0.00035 | $0.00731 |
| Opus 5 | $0.00017 | $0.00365 |
| Sonnet 5 | $0.00007 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
mainframe-planning 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a comprehensive transformation guide that maps each mainframe dependency to its standard COBOL replacement.
This guide is a prerequisite for the actual transformation — DO NOT modify any code, only create the guide.
Output Format
Document each mainframe-specific construct with:
- Pattern: The mainframe construct (e.g.,
EXEC CICS READ FILE(...)) - Replacement: The standard COBOL equivalent
- Error Handling: How to replicate the mainframe's error behavior
- Map CICS RESP/RESP2 codes to FILE STATUS equivalents
- Specify which FILE STATUS values to check (e.g., 00=success, 23=not found, 35=file not exists)
- Resource Cleanup: Any cleanup the replacement requires (CICS auto-manages resources; file I/O does not)
- Edge Cases: Behavior differences between mainframe and standard COBOL
Constructs to Address
Data Operations (CICS/IMS/VSAM)
- READ, WRITE, REWRITE, DELETE operations
- STARTBR, READNEXT, READPREV (browse operations)
- CICS error handling: HANDLE CONDITION, RESP/RESP2 options
- VSAM → sequential or indexed file I/O
UI/Terminal Operations (BMS maps, screens)
- SEND MAP, RECEIVE MAP → these can be MOCKED or stubbed
- Screen I/O is not needed for business logic validation
- Document how to replace with simple ACCEPT/DISPLAY or test harness stubs
- Focus on preserving the data flow, not the UI interaction
Other Mainframe Constructs
- Mainframe data types (COMP-3 packed decimal, etc.)
- JCL-embedded constructs
- IMS calls (if present)
Critical Requirements
- Every CICS command that can fail MUST have an error handling replacement documented
- UI operations should be clearly marked as "mock/stub" so the agent doesn't get stuck on them
- Prefer: file-based I/O over mainframe I/O, standard data types over mainframe types
Common Mappings Reference
FILE STATUS Codes
| Code | Meaning | CICS Equivalent |
|---|---|---|
| 00 | Success | Normal completion |
| 23 | Record not found | NOTFND condition |
| 35 | File does not exist | NOTOPEN condition |
| 22 | Duplicate key | DUPREC condition |
| 3x | I/O errors | Various IOERR conditions |
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.
- 2d ago First seen · 79 lines · 35 tokens per session scan A a6e64ed01595
mainframe-planning is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 731 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…