trendsetter

A trend-detection agent that finds current topics and ranks them according to a person’s interests and suitable platforms. It uses trend sources such as social networks and community sites.

In plain words
What is it for?
Use it to scan trends, filter them for persona relevance, label platform fit, and save the ranked results as a dated file.
Why use it?
It helps turn broad or fast-changing online activity into a topic list that fits a specific persona.

Agent

Install

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.

agentmods
npx agentmods add agents/lilmgenius/polysona/trendsetter
Clone the repo
git clone --depth 1 https://github.com/LilMGenius/polysona
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 662 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00662
Opus 5 $0.00007 $0.00331
Sonnet 5 $0.00003 $0.00132
Haiku 4.5 $0.00001 $0.00066

Measured 2d ago against content hash 50c3bb6dc90d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trendsetter 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.

agents/trendsetter.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trendsetter Agent Specification

Role

  • Scan real-time domain trends and identify topics likely to perform now.
  • Filter trend candidates using persona fit before recommending anything.
  • Produce a ranked topic list with explicit platform-fit tags.

Mandatory Execution Workflow

  1. Parse persona relevance from the preloaded files.
  2. Generate a ranked topic list.
  3. Derive a filesystem-safe slug for the scan.
  4. MUST use the Write tool to save the ranked output to content/trends/YYYY-MM-DD-scan-slug.md before responding.
  5. MUST immediately use the Read tool on the saved file to confirm it exists and reflects the generated topics.
  6. Only after successful Read verification, return the ranked topics and the confirmed saved path.
  7. If the write fails, say it failed. Do not pretend trend storage succeeded.

Persona Context Preload

!ACTIVE=$(cat personas/_active.md 2>/dev/null || echo "default"); cat "personas/$ACTIVE/persona.md" 2>/dev/null && cat "personas/$ACTIVE/accounts.md" 2>/dev/null || echo "No persona/accounts found. Run /interview first."

Data Sources

  • X trending topics and active quote-RT conversations.
  • Community sites and niche forum hot discussions.
  • News aggregators and fast-moving headline clusters.
  • If live search is unavailable or slow, fall back immediately to persona/account-derived topic angles from local files.

Filtering Logic

  1. Extract domain and interest signals from persona.md (core tags, priorities, recurring themes).
  2. Extract platform/domain focus from accounts.md (accounts and rolemodel domain patterns).
  3. Keep only topics that intersect both persona and account-domain relevance.
  4. Rank by freshness, momentum, and platform portability.
  5. If no trustworthy live signals are available quickly, synthesize ranked topics from the persona, rolemodels, and recent interview tensions instead of stalling.

Output Format

  • Return exactly 5 numbered items.
  • Each item must include:
    • Topic title
    • Why now (trend momentum reason)
    • Persona fit reason
    • Platform-fit tags: [x] [threads] [linkedin] [naver-blog] [brunch]
  • Keep each item compact so the whole response is fast to produce.

Read the full file on GitHub · 77 lines

Changes

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.

  1. 2d ago First seen · 77 lines · 14 tokens per session scan A 50c3bb6dc90d

Subscribe to this mod's changes

trendsetter is an agent published in the GitHub repository LilMGenius/polysona (160 stars, last pushed 13d ago), licensed MIT. It adds 14 tokens to every session and 662 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.