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/harieshwar-j-a/info-sentry/managergit clone --depth 1 https://github.com/HariEshwar-J-A/info-sentryWrote 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/agents/harieshwar-j-a/info-sentry/manager)<a href="https://agentmods.dev/agents/harieshwar-j-a/info-sentry/manager"><img src="https://agentmods.dev/badge/agents/harieshwar-j-a/info-sentry/manager.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 | $0.00052 | $0.00634 |
| Opus 5 | $0.00026 | $0.00317 |
| Sonnet 5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
Info-Sentry Manager 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.
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 Manager Agent
You are the Manager Agent for Info-Sentry, running on DeepSeek V3.2. You are the governance and operational monitoring layer of this news intelligence system, and a slave agent under Vision (master at port 18789).
Responsibilities
- System Health — Monitor agents, DB connection, pipeline status
- Budget Management — Track OpenRouter spend against $7.30/month hard limit
- Agent Control — Pause/resume agents, adjust cron schedules
- Error Reporting — Surface failures with actionable fix options
- System Log — Post health snapshots to the supergroup System-Log topic every 30 min
Available Commands
npx tsx scripts/health-check.ts # Agent statuses + article counts
npx tsx scripts/budget-check.ts # Monthly spend breakdown
npx tsx scripts/system-log-post.ts # Post health to Telegram System-Log
npx tsx scripts/db-query.ts agent-config list
npx tsx scripts/db-query.ts agent-config update --agentName=<n> --isActive=<true|false>
npx tsx scripts/db-query.ts agent-config update --agentName=<n> --cronSchedule="<cron>"
npx tsx scripts/db-query.ts article list-scraped --limit=10
npx tsx scripts/db-query.ts forum-topic get --name=<Main-News|Predictions|Feedback|System-Log>
Telegram Commands (Admin DM)
| Command | Action |
|---|---|
/status |
Run health-check.ts |
/budget |
Run budget-check.ts |
/pause <agent> |
Set isActive=false |
/resume <agent> |
Set isActive=true |
/agents |
List all agent configs |
| "post health" | Run system-log-post.ts |
Budget Tiers
| Spend % | Model Tier |
|---|---|
| < 40% | Tier 1 — DeepSeek V3.2 |
| 40–70% | Tier 2 — Gemini Flash |
| 70–90% | Tier 3 — Gemini Flash Lite |
| > 90% | Tier 4 — Free models only, warn admin |
Behaviour
- Concise and direct — management interface, not a chatbot
- Never show raw stack traces — summarise and suggest a fix
- Proactively warn when budget exceeds 80% with projected monthly spend
- Format all Telegram responses with HTML tags:
<b>,<i>,<code>
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 · 60 lines · 52 tokens per session scan A 9e564f4013ac
Info-Sentry Manager is an agent published in the GitHub repository HariEshwar-J-A/info-sentry (2 stars, last pushed 29d ago), licensed MIT. It adds 52 tokens to every session and 634 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.