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/agrc/agent-skills/ugrc-pythonnpx skills add agrc/agent-skills --skill ugrc-pythongit clone --depth 1 https://github.com/agrc/agent-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 | $0.00015 | $0.00621 |
| Opus 5 | $0.00008 | $0.00311 |
| Sonnet 5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
ugrc-python 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 2d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prefer the pathlib library over the older os.path module for handling filesystem paths. Be aware that the arcpy library does not support pathlib.Path objects directly prior to version 3.7; you will need to convert them to strings using str(path). In version 3.7 and later, arcpy can handle pathlib.Path objects directly and can even be set to return them by default using this ArcPy environment setting:
arcpy.env.returnPathlib = True
Linting and Formatting
Use ruff for linting and formatting with the following configuration:
[tool.ruff.lint]
extend-select = ["I"]
If the current project does not implement this exact configuration, offer to migrate it and fix any resulting issues.
CI Coverage
When a Python project uses Codecov, ensure that the test job which generates and uploads coverage runs on both pull requests and pushes to the default branch. Uploading coverage only from pull requests leaves Codecov's default-branch baseline stale, which produces reports stating that the base is many commits behind main.
When the same setup, lint, test, and coverage-upload steps appear in more than one workflow, extract them to a local composite action such as .github/actions/test-and-coverage/action.yml. Keep actions/checkout in each calling workflow because a local action is unavailable until the repository has been checked out. Pass the Codecov token to the action through a required input; do not embed repository secrets in the action definition.
Packaging Migration
When a project uses a legacy setup.py, offer to migrate its packaging configuration to pyproject.toml; do not perform this migration automatically. If the user approves, make the migration in a separate commit from unrelated changes.
Preserve the existing package metadata, dependencies, optional dependency groups, and package-discovery configuration. Upgrade the build backend to Hatchling when the user approves: use requires = ["hatchling"] and build-backend = "hatchling.build", then replace setuptools-specific configuration with the equivalent Hatchling configuration. Update CI cache dependency paths that reference setup.py to reference pyproject.toml. Remove obsolete setup.py configuration only after the declarative configuration is complete, and validate the migration by building source and wheel distributions and running the project's tests and Ruff checks.
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.
- 2d ago First seen · 38 lines · 15 tokens per session scan A 8a49dcedb69f
ugrc-python is a skill published in the GitHub repository agrc/agent-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 15 tokens to every session and 621 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
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-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
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.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
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…
quick-recap
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.