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/vladkesler/initrunner/servicesgit clone --depth 1 https://github.com/vladkesler/initrunnerWhat 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 | $0.00000 | $0.00922 |
| Opus 5 | $0.00000 | $0.00461 |
| Sonnet 5 | $0.00000 | $0.00184 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
services 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Always-on Services
Services are curated always-on agents: start once, they run on a schedule, report status, and stop without requiring YAML. Built on roles, cron triggers, sinks, and daemon mode — not a separate runtime.
Prerequisites
- Linux (process supervision is Linux-only in v1)
- A configured model provider (
initrunner setupor env keys) - For
collector: web search, which InitRunner offers to install on the first run
Quick start
# See what's available
initrunner service list
# Start collector (needs web search + a provider)
initrunner service start collector acme.com
# Or with explicit schedule / sink
initrunner service start collector acme.com \
--every daily \
--sink file:./collector-report.md
# Health
initrunner service status collector
# Force one cycle without waiting for cron
initrunner service run collector
# Stop (keep instance) or purge local files
initrunner service stop collector
initrunner service stop collector --purge
Commands
| Command | What it does |
|---|---|
service list |
Catalog + local status |
service info <slug> |
Params, requires, defaults |
service start <slug> [primary] |
Materialize + start daemon |
service status <slug> |
State, process health (with the daemon's RSS), last run, cost |
service run <slug> |
One-shot tick (briefly stops daemon if running) |
service stop [--purge] |
Stop daemon; --purge deletes instance dir |
service logs <slug> |
Daemon log tail |
Start options
| Flag | Meaning |
|---|---|
| positional | Value for the service primary_param (e.g. target) |
--set key=value |
Any declared param (duplicate keys rejected) |
--every |
hourly / daily / weekly / raw 5-field cron |
--sink file:/path or webhook:url |
Replace entire sink set (repeatable) |
Do not pass the primary both as a positional and via --set.
Shipped services
collector
Continuous monitoring for one target. Searches and reads public sources, diffs against memory, writes a brief when something material 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.
- yesterday First seen · 107 lines · 0 tokens per session scan A 888368904ea5
services is an agent published in the GitHub repository vladkesler/initrunner (41 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 922 tokens. 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 2026-08-30.
Other agents, from other repositories
unittest-generator
Use this agent when you need to create unit tests for your code in unittest.TestCase format, organized in a tests folder with concept-based subfolders. Examples: Context: User has just written a new authentication module and needs comprehensive unit tests. user: 'I just finished writing my user authentication…
harness-radar
Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the best-of-Agent-Harnesses dataset, which rescores itself every week. Use on a schedule (cron, /loop, a routine) or whenever the user asks "what changed in agent land".
ecosystem-doc-bridge-corpus-scanner
Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.
content-newsletter-author
Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.
ecosystem-registry-eval-author
Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.
application-patterns-wave-06
Wave 06 adds practical workflows for agency operations, clinical drafting, privacy, content, data, infrastructure, education, commerce, finance, people, insurance, legal review, operations, product, research, and security. Every pattern below uses synthetic input and is a starting point for inspection, not evidence of…