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/jimmc414/claude-code-plugin-marketplace/fallback-compatibilitynpx skills add jimmc414/claude-code-plugin-marketplace --skill fallback-compatibilitygit clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplaceWrote 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/jimmc414/claude-code-plugin-marketplace/fallback-compatibility)<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/fallback-compatibility"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/fallback-compatibility.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00543 |
| Opus 5 | $0.00012 | $0.00271 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
fallback-compatibility 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 6d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fallback-compatibility
When to Use
- Supporting multiple Python versions
- Optional dependency handling
- Feature detection
- Graceful degradation
When NOT to Use
- Single Python version target
- Required dependency (should fail if missing)
- Over-engineering simple code
The Pattern
Try preferred import/feature, fall back to alternative.
# Python version compatibility
try:
from functools import cache
except ImportError:
from functools import lru_cache
cache = lru_cache(None)
# Optional dependency
try:
import numpy as np
HAS_NUMPY = True
except ImportError:
HAS_NUMPY = False
def process(data):
if HAS_NUMPY:
return np.array(data).mean()
else:
return sum(data) / len(data)
Example (from pytudes)
# beal.py - math.gcd location changed between versions
try:
from math import gcd # Python 3.5+
except ImportError:
from fractions import gcd # Python 2.7 and early 3.x
# ngrams.py - use available modules
try:
from functools import cache
except ImportError:
from functools import lru_cache
def cache(func):
return lru_cache(None)(func)
# Pattern for conditional features
try:
# Python 3.10+ pattern matching
def dispatch(x):
match x:
case int(): return handle_int(x)
case str(): return handle_str(x)
case _: return handle_other(x)
except SyntaxError:
# Fallback for older Python
def dispatch(x):
if isinstance(x, int):
return handle_int(x)
elif isinstance(x, str):
return handle_str(x)
else:
return handle_other(x)
# Graceful feature degradation
try:
import matplotlib.pyplot as plt
def plot(data):
plt.plot(data)
plt.show()
except ImportError:
def plot(data):
print("Plotting requires matplotlib")
print(f"Data: {data[:10]}...")
Key Principles
- Try modern first: Prefer newer, better APIs
- ImportError for missing: Standard exception for imports
- Create compatible API: Wrapper that works either way
- Flag for optional:
HAS_FEATUREpattern - Fail gracefully: Warn, don't crash
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.
- 6d ago First seen · 98 lines · 24 tokens per session scan A c55d3dd7b8b3
fallback-compatibility is a skill published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 543 once invoked, about $0.0001 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
clean-code
Use when the user writes new Python, or asks for review, refactor, or cleanup of Python code, names, comments/docstrings, functions, or tests. Applies Robert Martin's complete Clean Code catalog -- naming, functions, comments, DRY, boundary conditions, and tests -- to the code being changed.
biopython
Molecular biology toolkit. Use for FASTA parsing, sequence analysis, and translation.
rust-coding-standards
Rust coding standards, documentation authoring, content workflows, and quality patterns for systemprompt.io development.
extension-building
Build library extensions for systemprompt.io with Rust - architecture, traits, schemas, API routes, jobs, and code review.
rust-dev-guide
Entry point for rust-development — routes to the right sub-skill for your task.
csharp-source-generator
Use when writing, reviewing, debugging, or testing C# source generators and Roslyn incremental generators. Covers IIncrementalGenerator architecture, SyntaxProvider pipelines, generated-code snapshots with Verify, analyzer packaging, marker attributes, AnalyzerConfigOptionsProvider, SDK compatibility, diagnostics, and…