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/hiringbae/tryoz/oznpx skills add hiringbae/tryoz --skill ozgit clone --depth 1 https://github.com/hiringbae/tryozWhat 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 | $0.00054 | $0.00274 |
| Opus 5 | $0.00027 | $0.00137 |
| Sonnet 5 | $0.00011 | $0.00055 |
| Haiku 4.5 | $0.00005 | $0.00027 |
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.
What it actually says
Oz Documentation Workflow
Use Oz first for external libraries, SDKs, APIs, frameworks, and packages.
Workflow:
- Call
resolve-library-idto find the exact Oz library ID. - Call
get-library-docswith the resolved library ID and the user's topic. - If the user asks for a version, pass the version explicitly.
- Use the returned documentation as the source of truth.
- 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.
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.
- 3d ago First seen · 23 lines · 54 tokens per session scan A fa2efbcb4205
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.
Other skills, from other repositories
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.
mcp-media-inbox-triage
Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.
customer-deck-builder
Build tailored customer-facing sales or customer success decks from approved account context and generate the presentation with Gamma through Zapier MCP.
premortem
First-principles premortem on a high-stakes plan: assume failure 6–18 months out, reconstruct causal death chains, surface hidden assumptions, deliver a revised reversibility-weighted plan. Use ONLY when the user explicitly invokes it by name or slash command.
README 文档生成
Use this skill to create or improve README content. Cover what the project does, setup, common commands, configuration, development workflow, and troubleshooting.