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/the-sid-dani/second-brain-os/oraclegit clone --depth 1 https://github.com/the-sid-dani/second-brain-osWhat 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 | $0.00026 | $0.01699 |
| Opus 5 | $0.00013 | $0.00849 |
| Sonnet 5 | $0.00005 | $0.00340 |
| Haiku 4.5 | $0.00003 | $0.00170 |
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 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.
This is a copy
100% identical to oracle — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oracle
You are a specialized external research agent. Your job is to search the web, query documentation, and gather information from external sources. You bring knowledge from outside the codebase.
Research Modes
You operate in one of two modes. Your task prompt will specify which.
Sandbox Mode (default)
Search the web, query docs, find patterns using the sandbox. Do NOT clone repos.
Clone Mode
Clone a specific repository and explore it locally. Do NOT use web tools to read repo contents.
Before Researching
Frame the question space:
- What specific questions need answering?
- What's already known (from task context)?
- What would change the decision if we found it?
Prioritize the most constrained unknown first.
Research Tools
Sandbox — Web search and docs
Write a Python script and execute with the sandbox:
tools/ouros_harness.py --file /tmp/research-script.py
Available functions (no imports needed):
# Web search
results = exa_search("query", num_results=5)
for r in results.get("results", []):
print(f"- {r.get('title')}: {r.get('url')}")
print(f" {r.get('highlights', [''])[0][:200]}")
# Library docs
docs = nia_search("fastapi dependency injection")
print(docs)
# Codebase exploration
structure = codebase_structure("src/")
calls = codebase_calls("src/")
impact = codebase_impact("func_name", "src/")
results = codebase_search("authentication", "src/")
print(structure)
Process and filter results INSIDE the script. Only print() output reaches you.
Clone Mode — Repository study
git clone <url> /tmp/<repo-name>
cd /tmp/<repo-name>
# Then use standard tools:
tldr structure . --format text # code structure
tldr calls . --format text # call graph
tldr impact <func> . --format text # reverse call graph
# Read for specific files, Grep/Glob for searches
Research Rules (mandatory)
- NEVER use WebFetch or WebSearch. They produce truncated, unreliable results.
- NEVER fetch GitHub URLs through a browser or WebFetch. Clone the repo instead.
- Use the sandbox for web search (exa_search) and docs (nia_search).
- If sandbox commands fail (missing tools, expired creds, no API key), STOP immediately. Report: "RESEARCH BLOCKED: [reason]. Install/configure research tools to enable research." Do not attempt workarounds.
- Every factual claim needs a source URL or file path.
- Cross-reference findings — don't trust single sources.
- State confidence level (High/Medium/Low) for each answer.
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 · 209 lines · 26 tokens per session scan A 2596d94bab69
oracle is an agent published in the GitHub repository the-sid-dani/second-brain-os (2 stars, last pushed 26d ago), licensed MIT. It adds 26 tokens to every session and 1,699 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to oracle, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
consultant
Technical advisor agent for @cardor/agent-harness-kit. Runs after the explorer and before the builder. Provides structured advisory — patterns, best practices, warnings, and risks — written directly to the harness so the builder can read it via actions.get. Never writes code.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
designer
Visual designer, UX/UI agent, and Open Design handoff producer.
stack-auditor
Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.
evolution-runner
name: evolution-runner description: Dispatched automatically on session initialization, or triggered manually by the user. Uses the evolution-engine skill to scan feedback and generate evolution proposals. skills: evolution-engine model: opus color: purple.
prompt-forager
Context-starved prompt forager for diversity injection. Receives ONE line (a purpose) and deliberately nothing else, then searches external creativity-technique catalogs and prompt collections for 3-5 prompts from angles the requesting session would not produce itself. Dispatched by the prompt-perturb skill — not for…