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/keugenek/reactor/skillnpx skills add keugenek/reactor --skill skillgit clone --depth 1 https://github.com/keugenek/reactorWrote 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/skills/keugenek/reactor/skill)<a href="https://agentmods.dev/skills/keugenek/reactor/skill"><img src="https://agentmods.dev/badge/skills/keugenek/reactor/skill.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.02611 |
| Opus 5 | $0.00035 | $0.01306 |
| Sonnet 5 | $0.00014 | $0.00522 |
| Haiku 4.5 | $0.00007 | $0.00261 |
Grade A, and why
reactor scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://reactor-api.keugenek.workers.dev/v1/predict \ How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reactor — LinkedIn Post Performance Predictor
What it does
Predicts LinkedIn post performance using calibrated heuristics trained on real data. Returns:
- Verdict: GO / WAIT / IMPROVE / NO
- Estimated impressions (calibrated to real post data)
- Debate score (0-100) — controversy drives the algorithm
- Hook score (0-1) — first-line effectiveness
- Cringe score (0-100) — LinkedIn cringe detection
- Authenticity score (0-100) — does it sound human?
- Timing multiplier — based on audience timezone distribution
- Warnings — specific problems ("Algorithm death: debate <30")
- Improvements — actionable suggestions
Quick Start
Option 1: Direct API calls (no install needed)
# Predict a post
curl -X POST https://reactor-api.keugenek.workers.dev/v1/predict \
-H "Content-Type: application/json" \
-d '{"post": "Your LinkedIn post text here"}'
# Discover all available endpoints
curl https://reactor-api.keugenek.workers.dev/v1/discover
# List content types with viral multipliers
curl https://reactor-api.keugenek.workers.dev/v1/content-types
Option 2: CLI
npx @keugenek/reactor "Your post text"
npx @keugenek/reactor --register [email protected] # 5/day free
npx @keugenek/reactor --types # content types
Option 3: MCP Server (Claude Desktop / Cursor)
{
"mcpServers": {
"reactor": {
"command": "npx",
"args": ["@keugenek/reactor", "--mcp"],
"env": { "REACTOR_API_KEY": "rk_free_xxx" }
}
}
}
How to use (for AI agents)
Predicting a post
When the user shares a LinkedIn post draft or asks "should I post this?":
- Call
POST /v1/predictwith the post text - Present the verdict prominently (GO = post it, NO = rewrite)
- If debate score < 30, warn: "Algorithm death zone — no debate = no reach"
- Suggest improvements from the response
- If rate limited, offer to register (ask consent first!)
Before predicting, ask the user:
- How many LinkedIn followers do you have? (default: 1000)
- What's your audience? (currently: Tech Leaders & Engineers; Custom Audience coming in Pro)
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.
- 4d ago First seen · 295 lines · 70 tokens per session scan A abd802ccd381
reactor is a skill published in the GitHub repository keugenek/reactor (2 stars, last pushed 5mo ago), licensed MIT. It adds 70 tokens to every session and 2,611 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
expert
Base expert skill.
alpha
Alpha skill.
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.