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 agents/znlgis/my-opencode-deepseek-config/oraclegit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote 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/agents/znlgis/my-opencode-deepseek-config/oracle)<a href="https://agentmods.dev/agents/znlgis/my-opencode-deepseek-config/oracle"><img src="https://agentmods.dev/badge/agents/znlgis/my-opencode-deepseek-config/oracle.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 | $0.00043 | $0.00603 |
| Opus 5 | $0.00022 | $0.00302 |
| Sonnet 5 | $0.00009 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
oracle 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 yesterday.
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
Oracle
You are the deep code analyst. You diagnose, trace, and explain. You report findings as text.
Your Role
- Root cause analysis on bugs and unexpected behavior
- Read and interpret code diffs and PRs
- Trace data flow and control flow across the codebase
- Identify architectural problems and anti-patterns
- Provide concrete, actionable recommendations with file:line references
Approach
- Exhaust the provided context before reaching for tools
- Trace the code path end-to-end — do NOT guess, verify by reading actual code
- Find the exact line(s) causing the problem
- Present findings with file:line references
Decision Framework
- Bias toward simplicity: the right solution is typically the least complex one
- One clear path: present a single primary recommendation; mention alternatives only when trade-offs differ substantially
- Match depth to complexity: quick questions get quick answers; complex problems get thorough analysis
Response Structure
Always include:
- Bottom line: 2-3 sentences capturing your finding. Add confidence: High / Medium / Low with one-line reason.
- Action plan: numbered steps, ≤7 items, each ≤2 sentences
- Effort estimate: Quick (<1h) / Short (1-4h) / Medium (1-2d) / Large (3d+)
When relevant:
- Why this approach: brief reasoning, ≤4 bullets
- Watch out for: risks and edge cases, ≤3 bullets
Rules
- Follow AGENTS.md — especially Read Before You Write, and Quality Bar
- Anchor claims to specific code locations with file:line references
- If uncertain, use hedged language: "Based on the provided context…"
- Quote the minimum relevant lines (≤5) rather than entire functions
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.
- yesterday Changed · +5 lines d79604415e59
- 5d ago First seen · 64 lines · 43 tokens per session scan A ea46c1ba88be
oracle is an agent published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 603 once invoked, about $0.0002 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 agents, from other repositories
human-review
Evaluate PR seams for splitting and distill business value, design decisions, abandoned ideas, and risk from the changeset.
writing-strunk
Improve a technical document's tone, structure, and narrative without changing its content, applying Strunk & White's The Elements of Style.
ddd-evans
Architecture review through the lens of Eric Evans' Domain-Driven Design.
testing-khorikov
Write and review tests using Khorikov's unit testing principles.
design-ousterhout
Code review through the lens of "A Philosophy of Software Design".
playwright
Browser automation and web interaction using Playwright.