A guide for reading or changing the oly daemon's configuration, where a daemon is a background service that manages sessions. It covers configuration precedence, reload behavior, and prompt or session-resume hints.

Use it to inspect or update oly settings, check the effective state, test hot reloads, and confirm observable configuration changes.

It reduces configuration mistakes caused by editing the wrong file, using unsupported keys, or overlooking command-line overrides. It requires checking that a change actually took effect.

oly-daemon — Skill for Claude Code and Codex by slaveOftime/open-relay

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.

Any agent

npx skills add slaveOftime/open-relay --skill oly-daemon

Clone the repo

git clone --depth 1 https://github.com/slaveOftime/open-relay

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/slaveoftime/open-relay/oly-daemon/github.svg)](https://agentmods.dev/skills/slaveoftime/open-relay/oly-daemon)

Your own site

<a href="https://agentmods.dev/skills/slaveoftime/open-relay/oly-daemon"><img src="https://agentmods.dev/badge/skills/slaveoftime/open-relay/oly-daemon/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/slaveoftime/open-relay/oly-daemon"><img src="https://agentmods.dev/badge/skills/slaveoftime/open-relay/oly-daemon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,872 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.01872
Opus 5.5	$0.00016	$0.00749
Sonnet 5.5	$0.00008	$0.00374
Haiku 4.5	$0.00004	$0.00187

Measured today against content hash 97b9f85f7233, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oly-daemon 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 today.

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.

skills/oly-daemon/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configure the oly daemon

Configuration lives at <STATE_DIR>/config.json. Read the existing file before editing and preserve unrelated fields and generated secrets.

Flat JSON only: Keys are top-level, not JSON-with-comments and not nested under limits, notify, or web_push.
Validation: Malformed JSON, out-of-range values, invalid regexes, or removed byte-cap keys fail startup and reject hot reload (preserving the last good config on reload). Unknown keys are ignored with a warning naming each key.

1) Locate state and precedence

Run oly daemon status to inspect ROOT (<STATE_DIR>), LOGS, SESSIONS, HTTP, Auth, and ID-PUB-KEY.

Platform	Default state directory
Override	`$OLY_STATE_DIR` (must be set before daemon launch)
Windows	`%LOCALAPPDATA%\oly`
macOS	`~/Library/Application Support/oly`
Linux	`$XDG_STATE_HOME/oly` or `~/.local/state/oly`

Startup precedence is CLI flag > config.json > built-in default (for web_push_proxy: CLI > OLY_WEB_PUSH_PROXY > file > default). CLI flags keep winning across hot reloads for the lifetime of the daemon process.

Startup flag	Config field
`--bind <ADDR>`	`http_bind` (legacy alias: `bind`)
`--port <PORT>`	`http_port`
`--notification-hook <COMMAND>`	`notification_hook`
`--web-push-proxy <URL>`	`web_push_proxy`

--no-http and --no-auth are startup-only flags, not JSON keys.

2) Config keys and hot-reload boundaries

The daemon polls config.json mtime every 2 seconds. Duration settings in seconds are clamped/validated within 1..=31536000 (365 days).

Flat JSON key	Default	When it takes effect
`http_bind`	`127.0.0.1`	Restart required; must be an IP address
`http_port`	`15443`	Restart required; `1..=65535`
`notification_min_interval_seconds`	`10`	Live (`>= 1`)
`notification_hook`	none	Live; null/empty disables hook
`prompt_patterns`	`DEFAULT_PROMPT_PATTERNS`	Live on monitor tick; `[]` disables regex matching only
`resume_patterns`	`[]`	Live for future completed-output scans
`web_push_subject`	none	Live; rebuilds push channels
`web_push_vapid_public_key`	generated on first load	Live; rebuilds push channels
`web_push_vapid_private_key`	generated on first load	Live; secret
`web_push_proxy`	none	Live (unless overridden by CLI/env)
`log_level`	`info`	Live tracing-filter reload
`trusted_apps_enabled`	`false`	Live; enables trusted `/apps/` and `wwwroot` overrides
`max_running_sessions`	`50`	Live at session start (`0..=1000`; `0` blocks new starts)
`session_eviction_seconds`	`15`	Live runtime-eviction delay after exit (`>= 1`)
`screen_scrollback_rows`	`5000`	New sessions only (`0..=100000`)
`silence_seconds`	`10`	Live silence fallback (`>= 1`)
`stop_grace_seconds`	`5`	Live HTTP stop default when grace is omitted (`>= 1`)
`journal_retention_days`	`0`	Hourly sweep of stopped/killed/failed sessions (`0..=36500`; `0` keeps all)

Read the full file on GitHub · 132 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.

today Changed · -105 lines 97b9f85f7233
yesterday Changed · +2 lines e1ab299da3e5
2d ago Changed · +15 lines 0e2795e5c925
3d ago First seen · 220 lines · 40 tokens per session scan A c673f338351d

Subscribe to this mod's changes

oly-daemon is a skill published in the GitHub repository slaveOftime/open-relay (95 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,872 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.

Building agents Rust agentops ai-agents cli pty session-management

tui-explorer

Discover and replay terminal UI paths using agent-tui. Use when you need to launch a TUI app, explore navigation with bounded BFS, generate markdown acceptance tests, and verify those tests repeatedly. Do not use for web or desktop GUI automation.

pproenca/agent-tui · 54 tokens

agent-tui

Automate terminal UI (TUI) apps with agent-tui for testing, inspection, demos, and scripted interactions. Use when automating CLI/TUI flows, regression testing terminal apps, verifying interactive behavior, or extracting structured text from terminal UIs. Also use when asked what agent-tui is, how it works, or to demo…

pproenca/agent-tui · 89 tokens

contributor-onboarding

Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.

Hmbown/CodeWhale · 57 tokens

oly-daemon