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 Netflix-Skunkworks/oci-agent --skill writing-specsgit clone --depth 1 https://github.com/Netflix-Skunkworks/oci-agentWrote 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/netflix-skunkworks/oci-agent/writing-specs)<a href="https://agentmods.dev/skills/netflix-skunkworks/oci-agent/writing-specs"><img src="https://agentmods.dev/badge/skills/netflix-skunkworks/oci-agent/writing-specs/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/netflix-skunkworks/oci-agent/writing-specs"><img src="https://agentmods.dev/badge/skills/netflix-skunkworks/oci-agent/writing-specs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.00389 |
| Opus 5 | $0.00046 | $0.00195 |
| Sonnet 5 | $0.00018 | $0.00078 |
| Haiku 4.5 | $0.00009 | $0.00039 |
Grade A, and why
writing-specs 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 11d 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.
What it actually says
Process
- Confirm the plan or prompt names a tabular data source (table or CSV) with a treatment column and an outcome column. If either is missing, ask the user before drafting.
- specs are YAML files. Write them under
specs/{plan}/. Create the folder if it does not exist. - Point
analysis_notebookat an .ipynb file innotebooks/.
Validation (before saving)
- (skip for ACIC evals) Treatment and outcome columns exist in the data source
covariatesis non-empty and excludes the treatment and outcome columns.- At least one estimand toggle (
estimate_ate/estimate_att/estimate_ato) is true. ato_thresholdis in (0, 0.5).analysis_notebookexists innotebooks/.
Fields — general analyses
- data_path, treatment, outcome
- covariates
- estimate_ate, estimate_att, estimate_ato
- ato_threshold
- seed
- analysis_notebook
Fields — ACIC evals only
- acic_treatment, acic_response # replace data_path / treatment / outcome
- covariates
- seed
- estimate_ate, estimate_att, estimate_ato
- ato_threshold
- analysis_notebook: econml.ipynb
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.
- 11d ago First seen · 40 lines · 92 tokens per session scan A 8cd2b9ad20df
writing-specs is a skill published in the GitHub repository Netflix-Skunkworks/oci-agent (139 stars, last pushed 26d ago), licensed Apache-2.0. It adds 92 tokens to every session and 389 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.