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/catwillgh/mainframe/mainframe-python-backendnpx skills add CATWILLgh/MAINFRAME --skill mainframe-python-backendgit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWhat 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 | $0.00095 | $0.01068 |
| Opus 5 | $0.00048 | $0.00534 |
| Sonnet 5 | $0.00019 | $0.00214 |
| Haiku 4.5 | $0.00010 | $0.00107 |
Grade A, and why
mainframe-python-backend 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python backend engineering
Discover the active package, entrypoint, and installed stack before choosing an approach. Dependencies and repository names do not prove which framework, database path, worker, or test setup owns runtime behavior.
Work sequence
- Run the recon script as
python3 scripts/recon.py <package-root>from this skill, or follow recon.md manually. - Trace the changed behavior through its entrypoint, business rules, data or external boundary, side effects, callers, and observable output.
- Read only the references matching the active path and changed risk.
- Verify installed versions and version-sensitive behavior through current primary documentation or Context7.
- Use the project's native commands and the smallest faithful red-to-green test. Read testing.md when selecting a test level, changing existing tests, or separating local and CI checks.
Several frameworks, validators, database libraries, or test runners are observations, not automatic blockers. Resolve the active owner from imports, configuration, entrypoints, runtime wiring, and affected files. Escalate only an unresolved choice that changes product behavior, infrastructure, permissions, or the assigned result.
Complete the assigned behavior. Do not substitute TODOs, placeholders, skipped or weakened tests, suppressions, or deferred in-scope work for implementation.
Preserve or introduce deliberately
- In an established system, preserve its supported Python version, package manager, framework, architecture, validator, data layer, logging, contracts, and tests. Make the smallest coherent change; do not add a competing library or incidental migration.
- In a new isolated component, prefer a supported Python version, explicit boundaries, maintained libraries, typed public contracts, focused tests, and PostgreSQL when relational semantics are required. Select libraries from the real requirements rather than a universal preferred stack.
What ships with it
19 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.
- agents/openai.yaml 213 B
- references/api-conventions.md 2.3 KB
- references/auth-and-sessions.md 2.4 KB
- references/background-and-realtime.md 2.4 KB
- references/django.md 1.8 KB
- references/fastapi.md 1.9 KB
- references/files-and-integrations.md 2.9 KB
- references/flask.md 1.8 KB
- references/migrations.md 2.3 KB
- references/multitenancy.md 1.8 KB
- references/observability.md 1.9 KB
- references/postgres-concurrency.md 2.0 KB
- references/postgres.md 2.0 KB
- references/recon.md 1.6 KB
- references/redis.md 2.0 KB
- references/sqlalchemy.md 2.2 KB
- references/testing.md 2.7 KB
- references/validation.md 1.8 KB
- scripts/recon.py 5.9 KB runs code
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.
- yesterday First seen · 86 lines · 95 tokens per session scan A 3835c4316a4c
mainframe-python-backend is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 11d ago), licensed MIT. It adds 95 tokens to every session and 1,068 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 2026-08-31.
Other skills, from other repositories
discord-webhook
Send trading alerts, signals, and analysis summaries to Discord via webhook. Integrates with realtime-alert-pipeline, trading-brain, and trade-journal-analytics.
agentforge-protocol
Use when doing non-trivial coding with Hermes, OpenClaw, Claude Code, Codex CLI, or similar autonomous coding agents. Orchestrates Karpathy-style minimal-change discipline, grill-plan intake, TDD, systematic debugging, subagent-driven implementation, spikes, and pre-commit review into one end-to-end workflow.
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.