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/tweakoz/orkid/obt-buildnpx skills add tweakoz/orkid --skill obt-buildgit clone --depth 1 https://github.com/tweakoz/orkidWrote 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/tweakoz/orkid/obt-build)<a href="https://agentmods.dev/skills/tweakoz/orkid/obt-build"><img src="https://agentmods.dev/badge/skills/tweakoz/orkid/obt-build.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 | $0.00078 | $0.02637 |
| Opus 5 | $0.00039 | $0.01319 |
| Sonnet 5 | $0.00016 | $0.00527 |
| Haiku 4.5 | $0.00008 | $0.00264 |
Grade A, and why
obt-build 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 4d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OBT Build System Reference
OBT (Orkid Build Tools) is a Python-based build/dependency management system. It lives in the ork.build git repo and is installed as a pip package into a Python venv.
Repository & Installation
| Component | Path |
|---|---|
| ork.build repo (source) | ../ork.build (relative to orkid workspace) |
| Installed OBT modules | $OBT_VENV_DATA/modules/ |
| OBT Python package | $OBT_ORIGINAL_PYTHONPATH/obt/ |
| OBT scripts (bin_pub, always on PATH) | $OBT_VENV_DIR/bin/obt.*.py |
| OBT scripts (bin_priv, staging-only) | $OBT_VENV_DATA/bin_priv/ |
To mirror live changes from ork.build repo to the running installation:
manually copy modified files from the repo to the installed location. Do NOT use
pip install -e . — it has caused issues and risks breaking the twine/PyPI
deployment path that others depend on.
# Example: after editing modules/dep/pydefaults.py in ork.build repo
cp /path/to/ork.build/modules/dep/pydefaults.py $OBT_VENV_DIR/obt/modules/dep/pydefaults.py
| Repo path | Installed path |
|---|---|
ork.build/modules/dep/*.py |
$OBT_VENV_DATA/modules/dep/ |
ork.build/modules/obt/*.py |
$OBT_ORIGINAL_PYTHONPATH/obt/ |
ork.build/bin_priv/*.py |
$OBT_VENV_DATA/bin_priv/ |
ork.build/bin_pub/*.py |
$OBT_VENV_DATA/bin_pub/ |
PyPI deployment is managed via the ork.build repo's setup.py (package name: ork.build).
Do NOT break the twine path — many users depend on pip-deployed OBT.
CAUTION: a PyPI release reflects the tree it was cut from — pip install --upgrade
onto a seat carrying newer hand-mirrored files REGRESSES them (observed 2026-07-29:
0.0.319 reverted a seat's class-routing obt/net/client.py). Check what the release
contains before upgrading a patched seat.
Key Files (orkid side)
| Component | Location |
|---|---|
| Build Script | obt.project/bin/ork.build.py |
| Root CMake | CMakeLists.txt |
| Orkid CMake Macros | orkid.cmake |
| Core CMake | ork.core/CMakeLists.txt |
| Lev2 CMake | ork.lev2/CMakeLists.txt |
| ECS CMake | ork.ecs/CMakeLists.txt |
| Core Pyext CMake | ork.core/pyext/CMakeLists.txt |
| Lev2 Pyext CMake | ork.lev2/pyext/CMakeLists.txt |
| Env Init | obt.project/scripts/init_env.py (prepends obt.project/bin/ to PATH, making all ork.*.py scripts available) |
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.
- 4d ago First seen · 278 lines · 78 tokens per session scan A 80545bbfc156
obt-build is a skill published in the GitHub repository tweakoz/orkid (35 stars, last pushed 24d ago), licensed MIT. It adds 78 tokens to every session and 2,637 once invoked, about $0.0004 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 2026-09-01.
Other skills, from other repositories
dart-python
DART Python: dartpy bindings, nanobind, wheels, and API patterns.
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.
Ferramenta Python de Divisão de Áudio com GUI e FFmpeg Local
Cria um script Python completo com interface gráfica (Tkinter) para dividir arquivos de áudio em segmentos, utilizando um executável FFmpeg localizado na mesma pasta do script.
Pré-processamento de áudio para transcrição Whisper
Executa o pipeline de redução de ruído e normalização de volume em arquivos de áudio usando Python (bibliotecas como Silero, noisereduce, numpy e scipy) para otimizar a entrada para modelos de reconhecimento de voz como o Whisper.
typetype-development
TypeType development workflow, environment setup, testing, building, CI, and pre-commit checks. Use when setting up or preparing code for commit.
simpy-discrete-event
Use this Skill for discrete-event simulation with SimPy: M/M/c queues, manufacturing lines, resource contention, and confidence intervals via replications.