ultan-search

ultan-search is a skill for Claude Code, Codex from nickroci/ultan. It costs 132 tokens per session (629 once invoked), scanned A, original, MIT.

A search tool for finding and reading notes in the user's local Ultan memory library, a folder of Markdown files. It can open a named note with nearby notes or find notes by a text query.

In plain words
What is it for?
Use it to retrieve a note by path or wikilink, or search the library for topics such as coding preferences, project details, and past decisions.
Why use it?
It removes the need to remember where stored project knowledge lives or browse the folder manually. It also gives surrounding notes to help explain the context.

Skill for Claude CodeCodex

Part of the ultan plugin — 2 skills, 2 commands, 6 hooks shipped together

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.

agentmods
npx agentmods add skills/nickroci/ultan/ultan-search
Any agent
npx skills add nickroci/ultan --skill ultan-search
Clone the repo
git clone --depth 1 https://github.com/nickroci/ultan

Made for: Claude Code, Codex.

Or install ultan, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 6 hooks.

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.

agentmods badge for ultan-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/nickroci/ultan/ultan-search.svg)](https://agentmods.dev/skills/nickroci/ultan/ultan-search)
Your own site
<a href="https://agentmods.dev/skills/nickroci/ultan/ultan-search"><img src="https://agentmods.dev/badge/skills/nickroci/ultan/ultan-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00132 $0.00629
Opus 5 $0.00066 $0.00315
Sonnet 5 $0.00026 $0.00126
Haiku 4.5 $0.00013 $0.00063

Measured 4d ago against content hash 0e943b4ae449, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ultan-search 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (search.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ultan-search/SKILL.md · 43 lines

What it actually says

Talks to the running agent-mem-daemon over its Unix socket and returns either a single entry (with browseable neighbours) or a ranked list of matches.

Usage

Invoke with one argument — the script auto-detects mode:

  • Wikilink or path[[projects/agent-mem/concepts/README]], projects/agent-mem/concepts/README, global/conventions/use-uv.md, etc. → returns the entry's full content plus siblings, subfolders, and parent README excerpt so you can navigate to neighbours without a second call.
  • Free-text queryoptimizer pruning, tier 3 interrupts, prefer python over javascript, etc. → returns top-8 BM25-ranked entries with score + snippet.

Explicit prefixes win if auto-detection is wrong: path:<x> or query:<x>.

Running it

Run the search.py that sits in this skill's own directory (the directory containing this SKILL.md — shown in the skill listing):

python "<this-skill-dir>/search.py" "<wikilink-or-query>"

Use Bash to run this — the script writes the result as markdown to stdout. It is stdlib-only; any python3 works.

When NOT to use this skill

  • You want a synthesised answer fusing multiple entries — use /ultan-advisor <question> instead. The advisor runs Sonnet (deep search) + Opus (synthesis) to produce a single referenced answer; this skill is the raw-fetch primitive.
  • The priming snippet you already received in additionalContext covers the question — don't drill down redundantly.
  • You're trying to write to the library — use /ultan <text> or let the curator capture it from conversation; this skill is read-only.

Daemon dependency

This skill requires the agent-mem daemon to be running. If the socket isn't present at ${AGENT_MEM_HOME:-~/.agent-mem}/priming.sock, the script prints a clear error. With the Ultan plugin installed the daemon lazy-starts on its own — retry after a turn or two; from source, start it with uv run agent-mem-daemon -v.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 4d ago First seen · 43 lines · 132 tokens per session scan A 0e943b4ae449

Subscribe to this mod's changes

ultan-search is a skill published in the GitHub repository nickroci/ultan (4 stars, last pushed 2mo ago), licensed MIT. It adds 132 tokens to every session and 629 once invoked, about $0.0007 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.