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 instructions/lilmgenius/polysona/agents-mdgit clone --depth 1 https://github.com/LilMGenius/polysonaWhat 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 | $0.00611 | $0.00611 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
polysona AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polysona — Build and run multiple personas across any AI agent.
Agent Catalog
| Name | Role | Invocation Method | Key Capabilities |
|---|---|---|---|
| profiler | Deep psychology interviewer | Codex: $interview / Claude Code: /interview |
10-framework interview flow, defense-bypass prompts, interview-log extraction |
| trendsetter | Trend detector | Codex: $trend / Claude Code: /trend |
Domain trend scanning, topic prioritization, platform-fit filtering |
| content-writer | Platform content generator | Codex: $content [platform] / Claude Code: /content [platform] |
Persona-conditioned drafting, platform pattern adaptation, CTA shaping |
| virtual-follower | QA simulator (context:fork) |
Codex: $qa / Claude Code: /qa |
Multi-audience simulation, rolemodel-gap scoring, TOP 5 draft recommendation |
| admin | Publisher and tracker | Codex: $publish / Claude Code: /publish |
Publishing flow, scheduling, metadata capture, feedback loop updates |
Architecture Overview
┌─────────────────────────────────────────────────────────────┐
│ POLYSONA │
│ Build and run multiple personas across any AI agent. │
│ │
│ SETUP (one-time / periodic refresh) │
│ ① profiler -> interview log extraction │
│ -> Polysona structuring engine │
│ -> persona.md + nuance.md + accounts.md │
│ │
│ LOOP (per content cycle) │
│ ② trendsetter -> ③ content-writer -> ④ virtual-follower │
│ -> user selection -> ⑤ admin (publish + tracking) │
└─────────────────────────────────────────────────────────────┘
Quick Start (Codex)
AGENTS.mdis auto-recognized by Codex-compatible workflows.- Codex auto-discovers repo skills from
.agents/skills. This repo mirrorsskills/there for Codex compatibility. - After editing
skills/, resync withnode ./scripts/sync-codex-skills.mjsorbun run codex:skills:sync. - Use
$interview,$introduce,$trend,$content [platform],$qa,$publish,$status,$export. - Keep persona data in
personas/{id}/using PLOON format.
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 · 48 lines · 611 tokens per session scan A 1d0c5d0e7f24
polysona AGENTS.md is an instructions file published in the GitHub repository LilMGenius/polysona (160 stars, last pushed 13d ago), licensed MIT. It adds 611 tokens to every session, about $0.0031 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 instructions, from other repositories
intelligent-terminal agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
connectonion AGENTS.md
AGENTS.md instructions for openonion/connectonion, covering agents.md, project overview, architecture, core components and key design patterns.
ironcurtain CLAUDE.md
Instructions for provos/ironcurtain, covering claude.md, general workflow, git & worktrees, git workflow and platform considerations.
agentsys CLAUDE.md
Claude Code instructions for agent-sh/agentsys, covering agentsys, critical rules, model selection, core priorities and dev commands.
epistemic-protocols AGENTS.md
Instructions for jongwony/epistemic-protocols, covering agents.md, northstar, settled directions, protocol index and runtime contract.
cyrus copilot-instructions.md
Copilot instructions for cyrusagents/cyrus: Note, there is a need to maintain the use of '--print' when running the claude exec commands because that is what makes it non-interactive.