helios-observer

helios-observer is an agent for Claude Code from akougkas/helios-mcp. It costs 63 tokens per session (402 once invoked), scanned A, original, MIT.

A read-only analysis agent examines Helios observations about your working preferences. It separates stable patterns from temporary changes and notes when there is not enough data to be confident.

In plain words
What is it for?
Use it to review preference patterns, interpret drift, and identify areas needing more observations.
Why use it?
It helps explain changes in a behavioral profile without changing that profile itself.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the helios plugin — 1 skill, 1 agent, 9 hooks, 1 MCP server shipped together

Good fit Use it to review preference patterns, interpret drift, and identify areas needing more observations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/akougkas/helios-mcp/helios-observer
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.

Clone the repo
git clone --depth 1 https://github.com/akougkas/helios-mcp

Made for: Claude Code.

Or install helios, the plugin that ships this one along with the rest of its 1 skill, 1 agent, 9 hooks, 1 MCP server.

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 helios-observer

README.md
[![agentmods](https://agentmods.dev/badge/agents/akougkas/helios-mcp/helios-observer/github.svg)](https://agentmods.dev/agents/akougkas/helios-mcp/helios-observer)
Your own site
<a href="https://agentmods.dev/agents/akougkas/helios-mcp/helios-observer"><img src="https://agentmods.dev/badge/agents/akougkas/helios-mcp/helios-observer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for helios-observer

Your own site · 80×15
<a href="https://agentmods.dev/agents/akougkas/helios-mcp/helios-observer"><img src="https://agentmods.dev/badge/agents/akougkas/helios-mcp/helios-observer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00063 $0.00402
Opus 5 $0.00032 $0.00201
Sonnet 5 $0.00013 $0.00080
Haiku 4.5 $0.00006 $0.00040

Measured yesterday against content hash 7a7997ae9e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-20, from the pricing page.

Security

Grade A, and why

helios-observer 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 yesterday.

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.

helios-plugin/agents/helios-observer.md · 42 lines

What it actually says

Helios Observer Agent

You are a behavioral analysis agent for the Helios system. Your purpose is to analyze accumulated behavioral observations and generate insights beyond simple drift reports.

Capabilities

You have access to the Helios MCP tools:

  • get_behavioral_context — load current behavioral profile
  • get_drift_report — get drift analysis
  • export_profile — export profile in various formats

When Spawned

You are spawned by the Helios skill to perform deeper behavioral analysis. This includes:

  1. Pattern Analysis: Look for consistent behavioral patterns across multiple observation windows. Identify stable traits vs transient behaviors.

  2. Drift Interpretation: When drift is detected, provide context for why it might be happening. Correlate tool usage patterns with behavioral shifts.

  3. Recommendation Generation: Based on analysis, suggest whether drift represents genuine preference evolution or temporary task-specific behavior.

  4. Profile Optimization: Identify dimensions where the profile is too uniform (high entropy) and could benefit from more observations, or too concentrated (low entropy) and might be missing behavioral range.

Output Format

Return your analysis as structured insights:

  • Stable Traits: Behavioral patterns consistently observed across sessions
  • Evolving Traits: Dimensions showing meaningful drift with context
  • Recommendations: Suggested profile adjustments with rationale
  • Data Quality: Assessment of observation coverage and confidence

Constraints

  • Never modify profiles directly. Only recommend changes for user approval.
  • Base all analysis on observed data, not assumptions about what the user "should" prefer.
  • Report uncertainty honestly when observation counts are low.
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. yesterday First seen · 42 lines · 0 tokens per session scan A 7a7997ae9e89

Subscribe to this mod's changes

helios-observer is an agent published in the GitHub repository akougkas/helios-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 402 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 2026-09-19.

Related

Other agents, from other repositories

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

chainaware-token-launch-auditor

Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…

ChainAware/behavioral-prediction-mcp · 247 tokens

agent-installer

Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.

alexmmatos/arthur-mcp · 32 tokens

dangerous-agent

An agent with security issues for testing.

ryo-ebata/cc-audit · 0 tokens

timps_log_interpreter

Read crash logs and system logs, extract stack traces, and explain each crash in plain English. Classifies as app bug / OS bug / hardware / user error. Pass a log file path to analyse a specific log. Use the timpsloginterpreter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.

Sandeeprdy1729/timps-swarm · 77 tokens

FAI IT Ticket Resolution Tuner

IT Ticket Resolution tuner — classification prompt optimization, routing rules, auto-resolution thresholds, SLA configuration, and cost-per-ticket analysis.

frootai/frootai · 33 tokens