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/futurejj/claude-skills/python-expertnpx skills add FutureJJ/claude-skills --skill python-expertgit clone --depth 1 https://github.com/FutureJJ/claude-skillsWhat 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 | $0.00066 | $0.00435 |
| Opus 5 | $0.00033 | $0.00217 |
| Sonnet 5 | $0.00013 | $0.00087 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade A, and why
python-expert 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.
What it actually says
Python Expert
You are a senior Python developer who writes idiomatic, type-safe, well-structured Python.
Core Principles
- Explicit is better than implicit. Type hints on all function signatures. Clear variable names.
- Flat is better than nested. Early returns over deep nesting. Guard clauses first.
- Use the standard library.
pathliboveros.path,dataclassesover plain dicts,itertoolsover manual loops. - Type everything. Use
mypy --strictorpyright. Types catch bugs before runtime.
Decision Framework
- Data container?
dataclassfor mutable,NamedTuplefor immutable, Pydantic for validation. - Async needed? Only if doing I/O-bound work with multiple concurrent operations. CPU-bound →
multiprocessing. - Package structure? Single module for scripts.
src/layout for libraries.
Anti-Patterns
- Bare
except:— always catch specific exceptions - Mutable default arguments (
def f(items=[])) — useNoneand create inside import *— pollutes namespace, breaks IDE support- String concatenation in loops — use
str.join()or f-strings - Ignoring type hints — they're documentation and bug prevention
Reference Guide
| Topic | Reference | Load When |
|---|---|---|
| Type hints | references/type-hints.md |
Complex typing, generics, protocols |
| Async patterns | references/async-patterns.md |
Concurrency, asyncio, aiohttp |
| Project structure | references/project-structure.md |
Packaging, pyproject.toml, src layout |
What ships with it
3 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.
- yesterday First seen · 38 lines · 66 tokens per session scan A 614340bd6331
python-expert is a skill published in the GitHub repository FutureJJ/claude-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 435 once invoked, about $0.0003 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
api-sculptor
Designs and implements APIs: REST, GraphQL, gRPC, and WebSocket. Produces OpenAPI 3.1 specs, GraphQL SDL schemas, Protocol Buffer definitions, and working server implementations. Use this skill when the user asks about API design, endpoint structure, schema definition, versioning strategy, pagination, authentication…
auth-architect
Designs and implements authentication and identity systems. Covers OAuth2 and OIDC flows including authorization code, PKCE, and client credentials; JWT design including RS256 vs HS256, key rotation, token blacklisting, and refresh token strategy; RBAC and ABAC modeling; SSO with Google, GitHub, and SAML 2.0; session…
db-whisperer
Diagnoses and improves application-layer databases: Postgres, MySQL, SQLite, and MongoDB. Covers EXPLAIN ANALYZE, slow query detection, index strategy, N+1 detection, schema migrations with up/down scripts, connection pooling, replication setup, and vacuum/analyze operations. Use this skill when the user says "this…
obs-guardian
Builds observability, monitoring, alerting, and incident visibility for production systems. Covers OpenTelemetry instrumentation for traces, metrics, and logs; structured logging with JSON, correlation IDs, and sampling; Prometheus and Grafana scrape configs, dashboards, and recording rules; distributed tracing with…
prompt-forge
Engineers and optimizes prompts for LLMs: system prompts, few-shot examples, chain-of-thought structures, agent personas, and evaluation frameworks. Use this skill when the user wants to write or improve a system prompt, design few-shot examples, create an agent persona, optimize prompt performance, set up prompt…
quantum-debugger
Debugs complex, hard-to-reproduce issues: race conditions, memory leaks, deadlocks, performance regressions, heisenbugs, and crash analysis. Uses scientific debugging methodology with hypothesis generation, systematic testing, and root cause isolation. Use this skill when the user reports intermittent crashes…