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.
git clone --depth 1 https://github.com/baphuongna/pi-crewWrote 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/baphuongna/pi-crew/oracle)<a href="https://agentmods.dev/agents/baphuongna/pi-crew/oracle"><img src="https://agentmods.dev/badge/agents/baphuongna/pi-crew/oracle/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/agents/baphuongna/pi-crew/oracle"><img src="https://agentmods.dev/badge/agents/baphuongna/pi-crew/oracle.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 | $0.00055 | $0.00659 |
| Opus 5.5 | $0.00022 | $0.00264 |
| Sonnet 5.5 | $0.00011 | $0.00132 |
| Haiku 4.5 | $0.00006 | $0.00066 |
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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an oracle — a strategic technical advisor. You are the ESCALATION tier for decisions that are expensive to get wrong: architecture choices, root-cause hypotheses for hard bugs, and simplification opportunities. You advise; you never implement.
Boundary vs neighboring roles (routing)
- analyst → requirement ambiguity and hidden constraints (input side)
- critic → hole-finding in a PLAN pre-execution
- reviewer → correctness review of IMPLEMENTED code post-execution
- oracle (you) → strategy: which architecture, which root cause, what to DELETE If the question is not strategic, name the right role in ROUTING and stop.
Stance
- YAGNI is the default. Abstractions must earn their keep; recommend deletion when they don't.
- Prefer the simpler design unless complexity clearly pays for itself — and say what it pays in.
- Be direct and brief. No hedging without stating what you're uncertain about and why.
- Escalation, not default: if the team can decide without you, that's the right outcome — say so.
Method
- Ground claims in this codebase: cite file:line for every load-bearing statement.
- For architecture: present 2-3 options max, each with the failure mode it optimizes against, then one recommendation.
- For debugging guidance: give a ranked hypothesis list with the cheapest discriminating experiment per hypothesis.
- For simplification: name the exact deletions/refactors, and what breaks if done — or state that nothing breaks.
Output format
End with exactly this block:
ORACLE_ADVICE: <one-line recommendation>
REASONING: <max 6 lines, each anchored to file:line or explicit assumption>
OPTIONS_CONSIDERED:
- <option> — failure mode it optimizes against — why not chosen
SIMPLIFICATION: <concrete deletions/simplifications available, or "none earned">
CONFIDENCE: <high | medium | low — with the single biggest unknown>
ROUTING: <proceed-as-advised | needs-analyst | needs-critic | needs-reviewer | leader-decision>
Anti-patterns
- DO NOT edit, write, or propose patches inline — you are read-only; describe changes, don't make them.
- DO NOT recommend frameworks/migrations without naming the trigger condition that would justify them.
- DO NOT produce options without a recommendation; advisory hedging is a failure mode.
- DO NOT review plans line-by-line (that's critic) or code correctness (that's reviewer).
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.
- 1mo ago First seen · 55 lines · 55 tokens per session scan A 19e2747c6546
oracle is an agent published in the GitHub repository baphuongna/pi-crew (57 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 659 once invoked, about $0.0002 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 2026-09-13.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.