oz

A documentation lookup workflow for external libraries, software development kits, frameworks, application programming interfaces, and packages.

In plain words
What is it for?
Use it to find the right library documentation and verify APIs, configuration keys, command-line options, versions, and code examples.
Why use it?
It checks version-specific reference material before suggesting code, reducing the risk of using made-up or outdated names, settings, flags, or examples.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/hiringbae/tryoz/oz
Any agent
npx skills add hiringbae/tryoz --skill oz
Clone the repo
git clone --depth 1 https://github.com/hiringbae/tryoz

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.00274
Opus 5 $0.00027 $0.00137
Sonnet 5 $0.00011 $0.00055
Haiku 4.5 $0.00005 $0.00027

Measured 3d ago against content hash fa2efbcb4205, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oz 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 3d 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.

templates/skills/oz/SKILL.md · 23 lines

What it actually says

Oz Documentation Workflow

Use Oz first for external libraries, SDKs, APIs, frameworks, and packages.

Workflow:

  1. Call resolve-library-id to find the exact Oz library ID.
  2. Call get-library-docs with the resolved library ID and the user's topic.
  3. If the user asks for a version, pass the version explicitly.
  4. Use the returned documentation as the source of truth.
  5. If Oz has no matching library, lacks the requested version, or returns insufficient context, then fall back to Context7, official docs, source repositories, or web search.

Reliability rules:

  • Do not hallucinate APIs, config keys, versions, CLI flags, or behavior.
  • If docs are missing or unclear, say that and fetch another authoritative source.
  • Stop calling Oz once enough context has been retrieved.
  • Do not repeatedly call tools with near-duplicate topics unless the first result was insufficient.
  • Prefer exact identifiers from Oz snippets: function names, env vars, routes, package names, error codes, config keys.
Changes

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.

  1. 3d ago First seen · 23 lines · 54 tokens per session scan A fa2efbcb4205

Subscribe to this mod's changes

oz is a skill published in the GitHub repository hiringbae/tryoz (15 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 274 once invoked, about $0.0003 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.

Related

Other skills, from other repositories