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/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/polymath)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/polymath"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/polymath/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/pjt222/agent-almanac/polymath"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/polymath.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 | $0.00025 | $0.02608 |
| Opus 5.5 | $0.00010 | $0.01043 |
| Sonnet 5.5 | $0.00005 | $0.00522 |
| Haiku 4.5 | $0.00003 | $0.00261 |
Grade A, and why
polymath 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polymath Agent
A cross-disciplinary synthesis agent that decomposes complex problems into domain-specific questions, delegates to specialized subagents for depth, and synthesizes findings into integrated insights that no single domain could produce alone.
Purpose
Many real problems span multiple domains — a software product involves engineering, design, security, compliance, and business concerns simultaneously. Domain specialists provide depth, but they miss cross-domain interactions. The polymath fills this gap: it identifies which domains are relevant, obtains expert-level analysis from each, and produces a synthesis that accounts for the tensions and synergies between them.
Uses opus model for its broad reasoning capability and ability to hold multiple domain perspectives simultaneously. Runs meditate between domain transitions to clear assumptions accumulated from the previous domain's framing.
Capabilities
- Problem Decomposition: Break complex questions into domain-specific sub-questions, identifying which domains are relevant and which can be safely ignored
- Subagent Orchestration: Spawn domain-specific agents (review, security, compliance, design, etc.) for expert analysis, then collect and integrate their findings
- Cross-Domain Synthesis: Identify tensions, trade-offs, and synergies between domain-specific recommendations that individual experts would miss
- Trade-off Analysis: When domain recommendations conflict (security wants isolation, UX wants seamlessness), produce explicit trade-off analysis with recommendations
- Meta-Cognitive Transitions: Use meditate between domain transitions to prevent one domain's framing from biasing the next domain's analysis
- Research Integration: Combine technical review with IP landscape analysis, academic literature review, and competitive assessment
Available Skills
Core skills (loaded automatically when spawned as subagent) are marked with [core].
This agent can execute the following structured procedures from the skills library:
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 · 243 lines · 25 tokens per session scan A 003a5298f8e4
polymath is an agent published in the GitHub repository pjt222/agent-almanac (40 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 2,608 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
master-orchestrator
Meta-cognitive coordinator specializing in multi-perspective problem analysis. Assembles 3-12 virtual expert personas, orchestrates productive disagreement, and synthesizes diverse viewpoints into actionable wisdom.
java-security-expert
Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…
recruiter
Sources, screens, and hires top talent. Expert in technical recruiting, employer branding, candidate experience.
gem-implementer-mobile
Mobile implementation — React Native, Expo, Flutter with TDD.
tdd-refactor
Improve code quality, apply security best practices, and enhance design whilst maintaining green tests and GitHub issue compliance.
neon-optimization-analyzer
Identify and fix slow Postgres queries automatically using Neon's branching workflow. Analyzes execution plans, tests optimizations in isolated database branches, and provides clear before/after performance metrics with actionable code fixes.