Borrowing it
Nothing to install: this file belongs to oxy-hq/oxygen. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oxy-hq/oxygen/main/.claude/skills/oxy-data-placement/SKILL.mdgit clone --depth 1 https://github.com/oxy-hq/oxygenWrote 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/oxy-hq/oxygen/oxy-data-placement)<a href="https://agentmods.dev/skills/oxy-hq/oxygen/oxy-data-placement"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-data-placement/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/oxy-hq/oxygen/oxy-data-placement"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-data-placement.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00113 | $0.01241 |
| Opus 5.5 | $0.00045 | $0.00496 |
| Sonnet 5.5 | $0.00023 | $0.00248 |
| Haiku 4.5 | $0.00011 | $0.00124 |
Grade A, and why
oxy-data-placement 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data placement: the shape of the data picks the store
Oxy is the control plane; each org is its own data plane. Full rule,
enforcement and backlog: internal-docs/data-placement.md. This skill is the
decision, not the reference.
Oxy's Postgres holds only what runs the platform
Identity and access, configuration (compiled definitions, secret references), what Oxy is doing (queue, leases, cursors, schedules), billing, audit, and signals that carry ids, never content.
Two questions decide a table:
- If this org left, would they expect to take these rows? Yes → data plane.
- Does Oxy need it before it knows which org is involved (routing, authz, scheduling)? Yes → control plane.
Both yes → split the row: the part Oxy routes on stays, the content moves.
Everything else: four shapes, four stores
| Shape | Store | Custom-app surface | Platform (Rust) path |
|---|---|---|---|
| Facts — happened, won't change: an order, a completed checklist, a reading | Workspace Airhouse (DuckLake) | ctx.airhouse.append / query / exec into app_<writer>; tables via airhouseMigrations |
Airway pipeline for external sources; a system-purpose Airhouse client for ingest (crates/cameras/src/airhouse/mod.rs) |
| Records an app edits — current state with constraints | Org OLTP Postgres | ctx.oltp.query / exec / tx; tables via migrations |
oxy_oltp writers: app:<slug> → app_<slug>, pipeline:<src> → raw_<src> |
| Files — bytes | App storage (S3) | ctx.storage |
object store, key in a record or fact |
| Customer warehouse — theirs | Theirs | ctx.warehouse.query; writes refused unless customerWarehouseWrites names the database with a reason |
read only |
Picking: bytes? → storage. Changes after it's written? No → fact; yes → record; both when history matters (record for "true now", fact for "what changed"). Already in the customer's warehouse? → read it there; copy it with Airway if it must join facts.
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 · 77 lines · 113 tokens per session scan A 4fa0e6f35c1b
oxy-data-placement is a skill published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 113 tokens to every session and 1,241 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
atlas-mssql
SQL Server specifics for Atlas (also Azure SQL and MSSQL): login, dev database and URL scope (mode=schema vs mode=database, the database query parameter), compatibility level and collation, system-generated constraint names, clustered index defaults and datetime2 precision in HCL, GO batches and the delimiter…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…