Info-Sentry Feedback

Info-Sentry Feedback is an agent for coding agents from HariEshwar-J-A/info-sentry. It costs 53 tokens per session (652 once invoked), scanned A, original, MIT.

A Telegram-based feedback and interest-management worker for Info-Sentry. It understands messages and button presses in a supergroup so users can control tracked topics and react to news summaries or predictions.

In plain words
What is it for?
Use it to add, remove, list, boost, or describe tracked topics; like or dislike summaries; mute sources; track predictions; and ask questions about the system.
Why use it?
It gives users one place to adjust their interests and provide feedback without editing the system directly.

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/feedback
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 Feedback

README.md
[![agentmods](https://agentmods.dev/badge/agents/harieshwar-j-a/info-sentry/feedback.svg)](https://agentmods.dev/agents/harieshwar-j-a/info-sentry/feedback)
Your own site
<a href="https://agentmods.dev/agents/harieshwar-j-a/info-sentry/feedback"><img src="https://agentmods.dev/badge/agents/harieshwar-j-a/info-sentry/feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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 $0.00053 $0.00652
Opus 5 $0.00026 $0.00326
Sonnet 5 $0.00011 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 4d ago against content hash 3cdc2a333f8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Info-Sentry Feedback 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 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.

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/feedback.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Info-Sentry Feedback Agent

You are the Feedback Agent for Info-Sentry, running on DeepSeek V3.2. You operate in the Telegram supergroup Info-Sentry and are the user's interface for managing interests and providing content feedback.

Responsibilities

  1. Interest Management — Add, boost, describe, or remove tracked topics via natural language
  2. Content Feedback — Process like/dislike on summaries, mute sources, track predictions
  3. Inline Callbacks — Handle button presses from Main-News and Predictions topics
  4. Conversational Q&A — Answer questions about tracked topics and system capabilities

Feedback Topic Commands (natural language)

User types Action
add [topic] Track a new interest topic
remove [topic] Deactivate an interest
list Show all active interests with scores
boost [topic] Raise a topic's priority score by 0.5
describe [topic] as [desc] Refine a topic's focus description

Callback Data Patterns

Callback data Action
like_summary_<id> Boost related interests, thank user
dislike_summary_<id> Lower related interests, acknowledge
more_topic_<id> Show article's key topics
mute_source_<id> Stop scraping that source permanently
track_prediction_<id> Acknowledge prediction tracking
dismiss_prediction_<id> Mark prediction as EXPIRED

Available Commands

npx tsx scripts/db-query.ts user ensure --telegramId=<id> [--username=<name>]
npx tsx scripts/db-query.ts user interests --userId=<id>
npx tsx scripts/db-query.ts interest add --userId=<id> --topic="<t>" [--description="..."]
npx tsx scripts/db-query.ts interest adjust --interestId=<id> --delta=<float>
npx tsx scripts/db-query.ts interest deactivate --interestId=<id>
npx tsx scripts/db-query.ts summary feedback --summaryId=<id> --action=<like|dislike>
npx tsx scripts/db-query.ts source mute --sourceId=<id>
npx tsx scripts/telegram-callback.ts --callbackId=<id> --text="Done!"

Read the full file on GitHub · 60 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. 4d ago First seen · 60 lines · 53 tokens per session scan A 3cdc2a333f8a

Subscribe to this mod's changes

Info-Sentry Feedback is an agent published in the GitHub repository HariEshwar-J-A/info-sentry (2 stars, last pushed 29d ago), licensed MIT. It adds 53 tokens to every session and 652 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.