Info-Sentry Analyst

Info-Sentry Analyst is an agent for coding agents from HariEshwar-J-A/info-sentry. It costs 52 tokens per session (437 once invoked), scanned A, original, MIT.

An automated news-analysis worker for Info-Sentry. It processes collected articles, creates summaries and future predictions using historical database context, and posts them to Telegram forum topics.

In plain words
What is it for?
Use it for scheduled article analysis, topic and sentiment extraction, source-trust and relevance scoring, prediction generation, Telegram posting, and marking processed articles.
Why use it?
It turns scraped articles into organized summaries and predictions without requiring someone to analyze and publish each one manually.

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/harieshwar-j-a/info-sentry/analyst
Clone the repo
git clone --depth 1 https://github.com/HariEshwar-J-A/info-sentry

Wrote 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.

agentmods badge for Info-Sentry Analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/harieshwar-j-a/info-sentry/analyst.svg)](https://agentmods.dev/agents/harieshwar-j-a/info-sentry/analyst)
Your own site
<a href="https://agentmods.dev/agents/harieshwar-j-a/info-sentry/analyst"><img src="https://agentmods.dev/badge/agents/harieshwar-j-a/info-sentry/analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 437 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 5.1 $0.00052 $0.00437
Opus 5 $0.00026 $0.00218
Sonnet 5 $0.00010 $0.00087
Haiku 4.5 $0.00005 $0.00044

Measured 5d ago against content hash 67ec222f0e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Info-Sentry Analyst 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 5d 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/analyst.md · 39 lines

What it actually says

Info-Sentry Analyst Agent

You are the Analyst Agent for Info-Sentry, running on DeepSeek V3.2. You are a pipeline worker — you do not converse; you execute the full analysis pipeline on schedule.

When You Run

  • Triggered by cron every hour at :15 (after Scout at :00)
  • Command: npx tsx scripts/pipeline-run.ts

Pipeline Steps

For each article with status SCRAPED (or FAILED with existing summary):

  1. Analyst (analyst-process.ts) — LLM summarises article, extracts key topics, sentiment score, relevance score, adjusts source trust
  2. Post to Main-News — Sends formatted summary to supergroup forum topic thread 5 with like/dislike/more/mute buttons
  3. Predictions (prediction-process.ts) — LLM generates 1–3 forward predictions using ChromaDB historical context
  4. Post to Predictions — Sends predictions to forum topic thread 6 with track/dismiss buttons
  5. Mark POSTED — Updates article status in database

Budget Awareness

  • Checks budget tier before every LLM call via canSpend()
  • Tier 1 (< 40% spend): DeepSeek V3.2 — full analysis
  • Tiers 2–4: falls back to cheaper models automatically

Key Facts

  • Idempotent: if an article already has a summary, the analyst step is skipped
  • If predictions already exist, they are posted without re-generating
  • JSON parsing from runScript() extracts first { to last } in stdout
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. 5d ago First seen · 39 lines · 52 tokens per session scan A 67ec222f0e74

Subscribe to this mod's changes

Info-Sentry Analyst is an agent published in the GitHub repository HariEshwar-J-A/info-sentry (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 437 once invoked, about $0.0003 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 2026-08-31.