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/treasure-data/td-skills/graflownpx skills add treasure-data/td-skills --skill graflowgit clone --depth 1 https://github.com/treasure-data/td-skillsWrote 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/treasure-data/td-skills/graflow)<a href="https://agentmods.dev/skills/treasure-data/td-skills/graflow"><img src="https://agentmods.dev/badge/skills/treasure-data/td-skills/graflow.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 | $0.00169 | $0.03876 |
| Opus 5 | $0.00084 | $0.01938 |
| Sonnet 5 | $0.00034 | $0.00775 |
| Haiku 4.5 | $0.00017 | $0.00388 |
Grade A, and why
graflow scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Subprocess** (CLI tools) | Call external CLIs directly — faster and more reliable than routing through an agent | `gh`, `tdx`, `curl`, `jq` | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
The subprocess type is important because spawning an agent session just to run a single CLI command adds significant latency and token cost. If the task is "fetch data from a CLI tool," `subprocess.run()` is the right ch The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
9 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.
- references/advanced-patterns.md 7.3 KB
- references/manifest-yml.md 7.0 KB
- references/studio-agent-bridge.md 12 KB
- references/workflow-patterns.md 6.5 KB
- templates/cs-health-check.py 2.7 KB runs code
- templates/hitl-approval.py 3.5 KB runs code
- templates/parallel-enrichment.py 3.3 KB runs code
- templates/sdr-sequence.py 3.2 KB runs code
- templates/simple-pipeline.py 1.9 KB runs code
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.
- 5d ago First seen · 389 lines · 169 tokens per session scan A 0f3bb1699282
graflow is a skill published in the GitHub repository treasure-data/td-skills (21 stars, last pushed yesterday), with no licence file. It adds 169 tokens to every session and 3,876 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.