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 markerikson/opencode-config-example --skill code-navigationgit clone --depth 1 https://github.com/markerikson/opencode-config-exampleWrote 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/markerikson/opencode-config-example/code-navigation)<a href="https://agentmods.dev/skills/markerikson/opencode-config-example/code-navigation"><img src="https://agentmods.dev/badge/skills/markerikson/opencode-config-example/code-navigation/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/markerikson/opencode-config-example/code-navigation"><img src="https://agentmods.dev/badge/skills/markerikson/opencode-config-example/code-navigation.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 | $0.00000 | $0.01064 |
| Opus 5.5 | $0.00000 | $0.00426 |
| Sonnet 5.5 | $0.00000 | $0.00213 |
| Haiku 4.5 | $0.00000 | $0.00106 |
Grade A, and why
code-navigation 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Navigation & File Reading
Full tool reference for navigating codebases. The AGENTS.md quick-reference table covers tool selection; this skill provides detailed usage patterns, workflows, and edge cases.
Grepika — Default Exploration Tool
Use grepika first for all code exploration and reading.
Commands
grepika_toc— directory tree overviewgrepika_search— find code patterns (regex or natural language). Requires index — rungrepika_indexfirst if results are empty/stale.grepika_outline— extract file structure (functions, classes, types). Always do this before reading code.grepika_getwithstart_line/end_line— read targeted sections. Use outline results to pick exact line ranges. Never omit line range on large files.grepika_context— see surrounding code at a search match locationgrepika_refs— find all references to a symbol/identifiergrepika_index— rebuild search index if results seem stale. Useforce=truefor full rebuild.
Core Workflow
grepika_outline → identify symbols of interest → grepika_get with line range → read only what's needed
Repeat as necessary. This keeps context lean.
Tilth — Structural / Definition Queries
When you need to know where something is defined or what calls what, prefer tilth over grepika.
Commands
tilth_read— smart file reading. Small files shown whole, large files auto-outlined with drillable line ranges.tilth_search— definition-first search. Finds where symbols are defined (not just string matches), shows surrounding structure, resolves callees inline.- Use
scopeparam to limit to a subdirectory - Multi-symbol: pass comma-separated names to trace across files in one call
- Callers:
kind: callersfinds all call sites using tree-sitter structural matching
- Use
tilth_deps— blast-radius check. Shows what a file imports and what other files use its exports. Use before breaking changes (renaming exports, changing signatures).
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.
- 1mo ago First seen · 82 lines · 0 tokens per session scan A 5d21bff64e60
code-navigation is a skill published in the GitHub repository markerikson/opencode-config-example (48 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,064 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.