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/dsswift/ion/discoverygit clone --depth 1 https://github.com/dsswift/ionWhat 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 | $0.00010 | $0.00599 |
| Opus 5 | $0.00005 | $0.00300 |
| Sonnet 5 | $0.00002 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
discovery 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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Discovery
The engine discovers agents by walking directories in a defined order. Project-level agents override user-level agents with the same name.
Discovery order
Directories are scanned in this order. The first directory wins for any given agent name.
| Priority | Directory | Description |
|---|---|---|
| 1 | .ion/agents/ |
Project-specific agents, relative to working directory |
| 2 | ~/.ion/agents/ |
User-level agents, shared across all projects |
| 3 | Extra directories | Additional paths specified via config |
Walk options
Discovery behavior is controlled by WalkOptions:
type WalkOptions struct {
IncludeUserDir bool // scan ~/.ion/agents/
IncludeProjectDir bool // scan .ion/agents/ relative to cwd
ExtraDirs []string // additional directories
Recursive bool // walk subdirectories
}
When Recursive is true (default for zero value), the walker descends into subdirectories. Only .md files are collected.
Deduplication
Agents are deduplicated by filename stem. If both .ion/agents/reviewer.md and ~/.ion/agents/reviewer.md exist, only the project-level file is loaded because project directories are scanned first.
This means project agents shadow user agents of the same name. Rename the project file if you need both.
Discovery process
- Walk -- Collect
.mdfile paths from all configured directories. - Parse -- Load each file and parse the frontmatter into an
AgentDef. - Build graph -- Assemble agent definitions into a parent-child graph with cycle detection.
Files that fail to parse (missing frontmatter fences, read errors) are logged and skipped. They do not block discovery of other agents.
graph, err := agentdiscovery.Discover(WalkOptions{
IncludeProjectDir: true,
IncludeUserDir: true,
})
Directory structure examples
Simple flat layout:
~/.ion/agents/
code-reviewer.md
summarizer.md
translator.md
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.
- 2d ago First seen · 85 lines · 10 tokens per session scan A 7a8120633b65
discovery is an agent published in the GitHub repository dsswift/ion (4 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 599 once invoked, about $0.0001 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
code_analyzer
Expert in analyzing code structure, complexity, design patterns, and providing refactoring recommendations. Uses CAST (Code Abstract Syntax Tree) tools for deep code understanding.
report_writer
Expert in synthesizing information from multiple sources into well-structured, professional reports. Specializes in technical documentation and analysis summaries.
web_searcher
Expert in searching and retrieving technical documentation, best practices, and relevant resources from the web. Synthesizes findings from multiple sources.
document_agent
Minimal example for creating and using AI Agents with aworld-cli.
building-agents
Create intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability.
reasoning-patterns
Every Promptise agent is powered by a Reasoning Graph. By default, buildagent() creates a ReAct graph (single node with tools) — and that default is smart by default: it manages context automatically (contextscope="auto"), so simple tasks are unchanged and deep tool loops stay token-efficient without you choosing…