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 skills add akougkas/helios-mcp --skill heliosgit clone --depth 1 https://github.com/akougkas/helios-mcpWrote 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/akougkas/helios-mcp/helios)<a href="https://agentmods.dev/skills/akougkas/helios-mcp/helios"><img src="https://agentmods.dev/badge/skills/akougkas/helios-mcp/helios/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.
<a href="https://agentmods.dev/skills/akougkas/helios-mcp/helios"><img src="https://agentmods.dev/badge/skills/akougkas/helios-mcp/helios.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.01630 |
| Opus 5 | $0.00017 | $0.00815 |
| Sonnet 5 | $0.00007 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
helios 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- helios — 92% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helios Behavioral Science
Helios observes your behavioral patterns and helps your agent learn your preferences. It detects when behavior drifts from your declared profile and proposes negotiated updates.
Commands
Route based on $ARGUMENTS:
/helios init [persona]— bootstrap Helios and onboard from~/.claude/CLAUDE.mdand the active output style/heliosor/helios status— show current behavioral profile/helios drift— check for behavioral drift/helios negotiate— review and accept/reject proposed changes/helios import <path>— import a personality file into Helios/helios export [format]— export behavioral profile (yaml, json, soulspec)
Init
When the user runs /helios init, or asks to (re)onboard from ~/.claude/CLAUDE.md: run the CLI directly. There's no MCP tool for this — it also sets the default persona, a filesystem-level change no MCP tool exposes.
helios-mcp init [persona]
Omit [persona] to reuse the already-configured default, or developer on a fresh install. Imports ~/.claude/CLAUDE.md and the active output style into that persona's user level as the authoritative source and makes it the default persona. Idempotent — rerunning overwrites the persona's user-level profile instead of duplicating it.
Session Start
!helios-mcp status 2>/dev/null || echo "Helios not yet bootstrapped"
At the beginning of each session, call get_behavioral_context to load the user's behavioral preferences. Apply these preferences to guide your communication style, epistemic approach, interaction patterns, and risk posture. Omit persona_name unless the user names a specific persona — it falls back to HELIOS_DIR/default_persona, then "default". Pass model with your own model id when you know it (it's usually stated in your system prompt, e.g. claude-sonnet-5) so the context can counter that specific model's observed tendencies rather than the average across models.
Tool: get_behavioral_context
Args: { "model": "<your model id, if known>" }
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.
- yesterday First seen · 124 lines · 35 tokens per session scan A f43eeb14d294
helios is a skill published in the GitHub repository akougkas/helios-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,630 once invoked, about $0.0002 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.
Other skills, from other repositories
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…
frontmcp-testing
Use for anything about testing FrontMCP servers: writing or running unit, integration, and E2E tests and reaching the 95%+ coverage bar. Covers Jest setup and coverage gating; unit-testing a ToolContext execute() with mock context, inputs, and Zod schema validation; testing resources and prompts; in-memory testing via…