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 skills add desirecore/market --skill python-runtimegit clone --depth 1 https://github.com/desirecore/marketWrote 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/desirecore/market/python-runtime)<a href="https://agentmods.dev/skills/desirecore/market/python-runtime"><img src="https://agentmods.dev/badge/skills/desirecore/market/python-runtime/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/desirecore/market/python-runtime"><img src="https://agentmods.dev/badge/skills/desirecore/market/python-runtime.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00228 | $0.02873 |
| Opus 5.5 | $0.00091 | $0.01149 |
| Sonnet 5.5 | $0.00046 | $0.00575 |
| Haiku 4.5 | $0.00023 | $0.00287 |
Grade B, and why
python-runtime scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Debian/Ubuntu | `sudo apt install python3 python3-pip python3-venv` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sk "${BASE}/python/available" How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
python-runtime Skill
L0: One-line Summary
When to use: The user needs to install Python / upgrade Python / switch
between multiple Python versions / configure pip / create virtual environments
(venv / pipx / conda) / troubleshoot python: command not found,
pip: command not found, PEP 668 "externally-managed", SSL certificates,
import failures, PATH anomalies, and other Python runtime issues; or when
another skill (docx / pdf / xlsx / pptx) reports "Python unavailable".
How to do it: Prefer DesireCore's built-in Hatch, executing through the four-tier fallback (HTTP API → Hatch CLI → system package manager brew/apt/dnf/winget → community solution pyenv).
L1: Overview and Use Cases
Capability Description
Procedural skill. Before each Python environment operation, first run scripts/probe-python.sh to obtain a JSON snapshot, then follow references/decision-tree (→ ../dev-environment-setup/references/decision-tree.md) to choose a path through the four-tier fallback.
Use Cases
- "python not found" / "pip not found"
- The user requests to install/upgrade Python
- The user requests multi-version management (3.10/3.11/3.12 switching)
- Create/activate/debug virtual environments (venv/pipx/conda)
- "externally-managed-environment" (PEP 668) error
- import failures, PATH issues, SSL certificate errors
- Other skills (docx/pdf/xlsx/pptx) report Python unavailable
Core Value
- DesireCore first: Hatch + HTTP API as mandatory L1/L2, avoiding pollution of system Python
- JSON-driven decisions: the probe script outputs structured data that Claude can parse directly
- Cross-platform consistency: macOS / Linux / Windows share a unified 4-tier fallback
L2: Detailed Specification
Step 1: Environment Probe (mandatory)
bash skills/python-runtime/scripts/probe-python.sh > /tmp/py-probe.json
cat /tmp/py-probe.json | jq .
For the meaning of output fields, see ../dev-environment-setup/references/probe-snapshot.md.
What ships with it
7 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.
- 24d ago Changed · +1 lines 868c9e534251
- 1mo ago First seen · 219 lines · 228 tokens per session scan B fb3b0b4b599c
python-runtime is a skill published in the GitHub repository desirecore/market (2 stars, last pushed yesterday), licensed MIT. It adds 228 tokens to every session and 2,873 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
uv-docs
Astral uv 0.11.x — fast Python package and project manager in Rust. Projects, scripts, tools, Python versions, pip interface.
mark2video
A function that adds a text watermark to a video. You can choose the watermark text, font size, font type, and color.
search_specify_type_file
A file-search function that finds files with a specified extension, such as .txt, .py, or .pdf, under a given folder.
course
A Python helper that displays tutorials, group information, source-code links, and other resources for the python-office library in a terminal.
tao-run-on-virtualenv
Run a Python training/eval script directly in an existing local virtualenv — no docker, no container. Implements the four-verb consumer contract (submit/status/logs/cancel) over a vendored process-lifecycle runner with durable on-disk state, PID-reuse-safe identity, and process-group cleanup. Use for docker-free local…
env-management
Environment variable patterns for Python (python-dotenv, Pydantic BaseSettings) and TypeScript (VITE, NEXTPUBLIC) projects — .env.example authorship, schema validation, mock/feature flags, and safe defaults — synthesized from lead-gen-engine and seo-geo-aeo-engine.