agentmods.dev

my-pi-omnisearch

my-pi-omnisearch is a skill for Claude Code, Codex from spences10/my-pi. It costs 29 tokens per session (326 once invoked), scanned A, original, MIT.

A procedure for researching current facts with a configured web-search service and checking the original pages behind search results. It distinguishes finding sources from verifying what those sources actually say.

In plain words
What is it for?
Finding official documentation and other sources, extracting page content, comparing conflicting evidence, and reporting uncertainty.
Why use it?
It reduces errors from relying on search snippets, unsupported summaries, or outdated information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 138repo +1 yesterday A scan 29 tokens original MIT

Good fit Finding official documentation and other sources, extracting page content, comparing conflicting evidence, and reporting uncertainty.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/spences10/my-pi/my-pi-omnisearch
View source ↗ spences10/my-pi my-pi.dev
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 spences10/my-pi --skill my-pi-omnisearch
Clone the repo
git clone --depth 1 https://github.com/spences10/my-pi

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.

agentmods badge for my-pi-omnisearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/spences10/my-pi/my-pi-omnisearch/github.svg)](https://agentmods.dev/skills/spences10/my-pi/my-pi-omnisearch)
Your own site
<a href="https://agentmods.dev/skills/spences10/my-pi/my-pi-omnisearch"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/my-pi-omnisearch/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.

agentmods 80×15 button for my-pi-omnisearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/spences10/my-pi/my-pi-omnisearch"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/my-pi-omnisearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 326 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00326
Opus 5.5 $0.00012 $0.00130
Sonnet 5.5 $0.00006 $0.00065
Haiku 4.5 $0.00003 $0.00033

Measured 5d ago against content hash 66a04e1907f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

my-pi-omnisearch 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 5d 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.

packages/pi-tool-guidance/skills/my-pi-omnisearch/SKILL.md · 35 lines

What it actually says

Verified web research

This skill supplies guidance, not an MCP server or provider credentials. Use the user's configured integration; do not install or configure one without authorization.

  1. Discover the actual namespace and tool names. In codemode use searchTools("web search"), describeNamespace(namespace), and describeTool(name); use tool search when that is the available route. Never assume hyphenated server names are valid JavaScript identifiers.
  2. Use web_search for discovery. Choose providers deliberately: Tavily for factual/cited searches, Brave or Kagi for operators, and Exa for semantic discovery, when those providers are available.
  3. Use web_extract to read actual source content before making claims. Search snippets alone are not verified evidence.
  4. Use ai_search when a synthesis with sources helps; verify important claims against those sources.
  5. Prefer official documentation, repositories, release notes, and source. State source conflicts, uncertainty, and partial tool failures.
  6. In codemode inspect MCP isError results, not just promise resolution.

If the server is unavailable, say so and use an available research tool without claiming Omnisearch verified the result. Never invent sources.

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. 5d ago First seen · 35 lines · 29 tokens per session scan A 66a04e1907f2

Subscribe to this mod's changes

my-pi-omnisearch is a skill published in the GitHub repository spences10/my-pi (138 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 326 once invoked, about $0.0001 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 2026-11-02.

LLMResearchTypeScriptclicoding-agentmcppi
Related

my-pi-omnisearch compared with skills from other repositories

my-pi-omnisearch next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
my-pi-omnisearchspences10/my-piSkill138yesterdayMITA29Claude Code, Codex
buncode-yeongyu/senpiSkill511yesterdayMITA237Claude Code, Codex
piznlgis/opengis-skillsSkill7610d agoMITB103Claude Code, Codex
tool-prompt-optimizationcan1357/oh-my-piSkill38kyesterdayMITA0Claude Code, Codex
semantic-compressioncan1357/oh-my-piSkill38kyesterdayMITA77Claude Code, Codex
optimization1jehuang/jcodeSkill22kyesterdayMITA52Claude Code
gpt-image-gencode-yeongyu/senpiSkill511yesterdayMITA66Claude Code, Codex