bhimsekhar/mainframe-re-framework
Config-driven Claude Code plugin for reverse engineering IBM mainframe applications (COBOL, CICS, JCL, BMS, VSAM) into modernisation-ready documentation
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit bhimsekhar/mainframe-re-framework/.claude ./rig-mainframe-re-framework # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/mainframe-analyst.md https://raw.githubusercontent.com/bhimsekhar/mainframe-re-framework/master/agents/mainframe-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/mainframe-orchestrator.md https://raw.githubusercontent.com/bhimsekhar/mainframe-re-framework/master/agents/mainframe-orchestrator.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(rm -rf*)",
"Bash(git push*)",
"Bash(git reset --hard*)",
"Bash(git checkout --*)",
"Bash(curl*)",
"Bash(wget*)",
"Bash(pip install*)",
"Bash(npm install*)",
"Bash(python setup.py*)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| mainframe-re env: PYTHONPATH | local / custom | 2.5k |
Subagents (2)
| mainframe-analyst | Specialised sub-agent for analysing a single mainframe artifact (COBOL program, copybook, JCL job, or BMS screen). Invoked by the orchestrator during batch analysis runs. Has access to all mainframe-r |
| mainframe-orchestrator | Orchestrator agent that coordinates batch analysis of multiple mainframe artifacts using parallel mainframe-analyst sub-agents. Manages the work queue from SQLite, dispatches work, collects results, a |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Write | bash hooks/validate_doc.sh |
| PostToolUse | Bash | bash hooks/track_progress.sh |
Slash commands (26)
/re-analyze/re-bms/re-cobol-batch/re-cobol-online/re-copybook/re-cross-ref/re-data-flow/re-index/re-init/re-jcl-job/re-jcl-proc/re-overview/re-report/re-analyze/re-bms/re-cobol-batch/re-cobol-online/re-copybook/re-cross-ref/re-data-flow/re-index/re-init/re-jcl-job/re-jcl-proc/re-overview/re-report
Permissions
deny (9)
Bash(rm -rf*)
Bash(git push*)
Bash(git reset --hard*)
Bash(git checkout --*)
Bash(curl*)
Bash(wget*)
Bash(pip install*)
Bash(npm install*)
Bash(python setup.py*)
ask (0)
—
allow (20)
Bash(python scripts/init_project.py*)
Bash(python scripts/run_analysis.py*)
Bash(python scripts/resume_analysis.py*)
Bash(python scripts/validate_docs.py*)
Bash(python scripts/index_docs.py*)
Bash(python scripts/generate_report.py*)
Bash(bash hooks/validate_doc.sh*)
Bash(bash hooks/track_progress.sh*)
Bash(python mcp/mainframe_server.py*)
Bash(sqlite3 db/*.sqlite*)
Bash(mkdir -p*)
Bash(ls*)
Bash(find * -name *.cbl*)
Bash(find * -name *.cpy*)
Bash(find * -name *.jcl*)
Bash(find * -name *.bms*)
Bash(wc -l*)
Bash(grep -r*)
Bash(grep -c*)
Bash(grep -l*)
Similar rigs
anomalyco/opencode
The open source coding agent.
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Pragmatist 4.2k tok ·
garrytan/gstack
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Pragmatist 8.8k tok ·