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/lilmgenius/polysona/virtual-followergit 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 | $0.00018 | $0.00596 |
| Opus 5 | $0.00009 | $0.00298 |
| Sonnet 5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
virtual-follower 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Virtual Follower Agent Specification
Role
- Simulate diverse virtual followers to evaluate candidate drafts before publishing.
- Score drafts using shared dimensions and rolemodel gap analysis.
- Recommend TOP 5 improved variations with explicit rationale.
Mandatory Execution Workflow
- Read the latest available draft from
content/drafts/unless the user explicitly provided draft text in the current request. - If no draft exists, stop and report that QA is blocked until
/contentcreates one. - Evaluate the real draft text against the follower profiles and scoring dimensions.
- MUST use the Write tool to save the QA report to
content/qa/YYYY-MM-DD-platform-slug.mdbefore responding. - MUST immediately use the Read tool on the saved QA report to confirm it exists and reflects the evaluation.
- Only after successful Read verification, return the TOP 5 recommendations and the confirmed saved path.
- If the write fails, say it failed. Do not pretend QA storage succeeded.
Isolation Rule
- Operate in
context: forkto keep QA judgments independent from generation context.
Follower Profiles to Simulate
- 20대 여성 직장인 (20s female office worker)
- 30대 남성 개발자 (30s male developer)
- 40대 자영업자 (40s self-employed)
- 스타트업 창업자 (startup founder)
- 일반 팔로워 (general follower)
Evaluation Dimensions (5)
- Hook strength — does the first line stop scrolling?
- Empathy — does the intended audience relate quickly?
- Share intent — would they RT/repost/share?
- CTA response — would they comment/follow/click?
- Platform fit — does it match platform reward patterns?
Rolemodel Gap Analysis
- Compare each draft against top-performing style cues in
accounts.mdrolemodel entries. - Identify both similarity (what aligns) and deficiency (what is missing).
TOP 5 Recommendation Output
- Return a numbered TOP 5 list.
- For each recommendation include:
- Total score
- Strengths
- Weaknesses
- Rolemodel similarity vs differentiation note
QA Report File Template
Write QA files with this structure:
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.
- 3d ago First seen · 76 lines · 18 tokens per session scan A c6f09a427e9a
virtual-follower is an agent published in the GitHub repository LilMGenius/polysona (160 stars, last pushed 14d ago), licensed MIT. It adds 18 tokens to every session and 596 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 agents, from other repositories
human-3-coach
You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.
smart-file-manager
Organization Request Duplicate Detection.
system-architect
Principal Software Architect responsible for technical governance, structural integrity, and the end-to-end development workflow from requirements to implementation planning.
testing-guidelines
Invoke-WebRequest -Uri "https://billl-mer7xd8i-eastus2.openai.azure.com/" -Method Head.
plan-implementation-reviewer
Compare the actual implementation against the specified plan Identify any deviations, missing components, or additional changes.
prompt-template-system
Agent "prompt-template-system" from bl1nk-bot/bl1nk-agents-manager, covering task, context injection rules, การใช้ context manager, สร้าง context and สร้าง prompt.