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 skills/lilmgenius/polysona/exportnpx skills add LilMGenius/polysona --skill exportgit 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 | $0.00020 | $0.00488 |
| Opus 5 | $0.00010 | $0.00244 |
| Sonnet 5 | $0.00004 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
export scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
!ACTIVE=$(cat personas/_active.md 2>/dev/null || echo "default"); cat "personas/$ACTIVE/persona.md" 2>/dev/null && cat "personas/$ACTIVE/nuance.md" 2>/dev/null || echo "No persona. Run /interview first."
Export Skill Protocol
$ARGUMENTS:
target—claude,agents, orboth
Parse target first:
claude→ write onlypersonas/{active}/generated/CLAUDE.generated.mdagents→ write onlypersonas/{active}/generated/AGENTS.generated.mdbothor empty → write both generated files
Export to CLAUDE.md template (target=claude or both)
Build personas/{active}/generated/CLAUDE.generated.md from persona + nuance sources:
- Work philosophy section: infer priority, approach, and risk stance from
persona.md - Decision-making priorities: infer ordering + energy bias from
persona.md - Tone rules: map
nuance.mdvoice into register rules and avoid-list - Context loading protocol: derive startup context from
persona.mdcore tags - Anti-patterns to avoid: convert
persona.mdanti field into explicit do-not rules - Add a header note that this file was generated and should be reviewed before copying into a project root.
Export to AGENTS.md template (target=agents or both)
Build Codex/OpenCode-compatible agent definitions:
- Include agent name, description, and invocation method
- Ground role split in persona domain expertise from
persona.mdcore tags - Keep entries portable across Codex/OpenCode style
AGENTS.md - Write the result to
personas/{active}/generated/AGENTS.generated.mdand add a generated-file header note.
Output
Write generated files to personas/{active}/generated/:
CLAUDE.generated.mdAGENTS.generated.md- Create the directory first if it does not exist.
- Re-read the saved file(s) and return the confirmed generated path(s).
Note: This persona is now portable. Drop it into any project.
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 · 45 lines · 20 tokens per session scan A 53e8c9d62160
export is a skill published in the GitHub repository LilMGenius/polysona (160 stars, last pushed 13d ago), licensed MIT. It adds 20 tokens to every session and 488 once invoked, about $0.0001 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 skills, from other repositories
self-improvement
บันทึกการเรียนรู้ ข้อผิดพลาด และการแก้ไขเพื่อการปรับปรุงอย่างต่อเนื่อง ใช้เมื่อ: (1) คำสั่งหรือการทำงานล้มเหลว (2) ผู้ใช้แก้ไขข้อมูล (3) ผู้ใช้ร้องขอความสามารถที่ไม่มี (4) API หรือเครื่องมือภายนอกล้มเหลว (5) พบแนวทางที่ดีกว่าสำหรับงานที่ทำซ้ำ หรือต้องการทบทวนการเรียนรู้ก่อนเริ่มงานสำคัญ.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
plugin-development
This skill should be used when creating plugins, writing skills, building commands, developing agents, or asking about "plugin development", "create skill", "write command", "build agent", "SKILL.md", "plugin structure", "progressive disclosure".
html-ppt-xhs-pastel-card
A personal manifesto: a year of saying yes — the premise, the scenes, the turn, and the meaning that lands. Built as a decision-grade story deck for community, talk audience.
html-ppt-xhs-white-editorial
A staff-engineer promotion packet — scope, the proof moments, the artifacts, and the impact that clears the bar. Built as a decision-grade career deck for manager, calibration committee.
html-ppt-zhangzara-8-bit-orbit
A gamer's journey building a retro-arcade collection — the obsession, the hunt, and what the machines came to mean. Built as a decision-grade story deck for friends, hobby community.