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/whynusn/typetype/typetype-developmentnpx skills add whynusn/typetype --skill typetype-developmentgit clone --depth 1 https://github.com/whynusn/typetypeWrote 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/whynusn/typetype/typetype-development)<a href="https://agentmods.dev/skills/whynusn/typetype/typetype-development"><img src="https://agentmods.dev/badge/skills/whynusn/typetype/typetype-development.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 | $0.00034 | $0.01264 |
| Opus 5 | $0.00017 | $0.00632 |
| Sonnet 5 | $0.00007 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade D, and why
typetype-development scanned grade D with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo usermod -aG input $USER Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeType Development
Quick Setup
Prerequisites: Python 3.12+, uv package manager
# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
# Clone + install
git clone <repo> && cd typetype && uv sync
# Run
uv run python main.py
First Files to Read
For a fast mental model of the current project, read these first:
main.pysrc/backend/presentation/bridge.pysrc/backend/presentation/adapters/text_adapter.pysrc/backend/application/usecases/load_text_usecase.pysrc/backend/application/gateways/text_source_gateway.pysrc/backend/domain/services/typing_service.py
Common Commands
# TESTING
uv run pytest # all tests
uv run pytest tests/test_file.py # single file
uv run pytest -v # verbose
# CODE QUALITY
uv run ruff check . # lint check
uv run ruff format --check . # format check
uv run ruff format . # auto format
# LOGGING
TYPETYPE_DEBUG=1 uv run python main.py # debug enabled
TYPETYPE_LOG_LEVEL=info uv run python main.py # set level: debug/info/warning/error/none
Pre-Commit Checklist (MUST DO)
Before commit, all must pass locally:
uv run pytest
uv run ruff check .
uv run ruff format --check .
Fix any failure before commit.
Commit Convention
Repository commits follow the Lore Commit Protocol: describe why first, then record constraints, rejected options, confidence, scope risk, and what was verified.
Recommended template:
<intent line: why this change was made>
<body: context, constraints, rationale>
Constraint: <external constraint>
Rejected: <alternative> | <reason>
Confidence: <low|medium|high>
Scope-risk: <narrow|moderate|broad>
Directive: <warning for future modifiers>
Tested: <what was verified>
Not-tested: <known gaps>
Packaging (Nuitka)
uv run python -m ensurepip --upgrade
uv pip install --upgrade nuitka
uv run python -m nuitka main.py \
--follow-imports \
--enable-plugin=pyside6 \
--include-qt-plugins=qml \
--include-package=RinUI \
--include-data-dir=RinUI=RinUI \
--include-data-dir=config=config \
--output-dir=deployment \
--quiet \
--noinclude-qt-translations \
--standalone \
--noinclude-dlls=libQt6WebEngine* \
--include-data-dir=src/qml=src/qml \
--include-data-dir=resources/texts=resources/texts \
--include-data-files=resources/images/TypeTypeLogo.png=resources/images/TypeTypeLogo.png \
--include-data-files=resources/fonts/HarmonyOS_Sans_SC_Regular-subset.ttf=resources/fonts/HarmonyOS_Sans_SC_Regular-subset.ttf \
--include-data-files=resources/fonts/LXGWWenKai-Regular-subset.ttf=resources/fonts/LXGWWenKai-Regular-subset.ttf \
--include-data-dir=resources/trainer=resources/trainer \
--include-data-dir=resources/ziti=resources/ziti
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 · 164 lines · 34 tokens per session scan D 661b6a0ed663
typetype-development is a skill published in the GitHub repository whynusn/typetype (11 stars, last pushed 18d ago), licensed MIT. It adds 34 tokens to every session and 1,264 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
add-crate
Add a new member crate to a Cargo workspace in this repo using the y5-template binary. Use whenever the user asks to add/create/scaffold a new crate, module, or workspace member (e.g. "add a crate under compositor.window", "scaffold action.foo"). Handles the chain-prefix naming convention and non-interactive…
commands-create-slash-command
Create or update Agent Zero slash commands for the built-in Commands plugin. Use when the user asks to add, edit, duplicate, or refine a reusable /command backed by YAML config plus text/python content files.
simple-modern-uv
Start, selectively modernize, fully migrate, or update Python projects using simple-modern-uv practices: uv, ruff, BasedPyright, pytest, GitHub Actions CI, and tag-driven PyPI publishing. Use when creating a Python project; adding selected tooling or repository practices to an existing project; migrating from Poetry…
hypersyn
How to author procedural content in orkid using HyperSyn (Reality Synthesizer) — a Python-as-DSL system for composing particle systems, 2D/3D procedural textures, mesh/SDF operations, and (eventually) audio/sequencer graphs into compact runtime experiences. Use when the user asks about HyperSyn, ptex2d, ptex3d…
pypi-ops
Publish Python packages to PyPI via OIDC Trusted Publishing (PEP 740 attestations, gh-action-pypi-publish) instead of stored tokens. Use for: invalid-publisher errors, pending-publisher 404s, uv publish/twine, TestPyPI, environment approval gates, and rotating/auditing publish tokens.
obt-build
Answer questions about OBT (Orkid Build Tools), dependency management (obt.dep..py commands), pydefaults, ork.build.py, CMake structure, ork.python environment, staging directories, pyext builds, environment variables, and the ork.build git repo. Use when the user asks about building, compiling, dependencies, pip…