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 ohong/agent-skills --skill search-xgit clone --depth 1 https://github.com/ohong/agent-skillsWrote 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/ohong/agent-skills/search-x)<a href="https://agentmods.dev/skills/ohong/agent-skills/search-x"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/search-x/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/ohong/agent-skills/search-x"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/search-x.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 | $0.00030 | $0.00442 |
| Opus 5 | $0.00015 | $0.00221 |
| Sonnet 5 | $0.00006 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
search-x 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 10d 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.
What it actually says
Search X
Find the actual post behind a noisy memory. Optimize for semantic triangulation and direct verification, not the first plausible keyword match.
Workflow
-
Build a compact semantic fingerprint:
- remembered thesis or emotional point;
- concrete anchors such as examples, names, links, dates, or screenshots;
- likely synonyms and category substitutions;
- details that may be wrong, including author, wording, or post type.
-
Search the strongest available surfaces:
- logged-in X for bookmarks, quote tabs, replies, profiles, and hidden posts;
- X live search for phrases, concepts, and operators;
- direct post or profile pages for surrounding context;
- web search for indexed snippets, mirrors, newsletters, or linked articles.
-
If a URL, author, or quoted post is known, inspect that literal path first. Open long candidates because previews may hide the decisive line. Record why a path fails before relaxing it.
-
Run query ladders instead of random rewrites. Read references/query-ladders.md for the ladder patterns, X operators, and common memory distortions.
-
Inspect each candidate against the whole fingerprint:
- Does it express the thesis, not merely share one keyword?
- Are the remembered examples exact, categorical, or adjacent?
- Is the claim carried by a quote, reply, thread, screenshot, or linked article?
- Does the author context and date fit?
-
Open the direct status URL and verify it on the live page. Search assistants may suggest clues, but never treat their answer as verification.
Result
Return:
- author display name and handle;
- direct post URL;
- a short paraphrase of the decisive match;
- any mismatch against the user's remembered details.
If no post is verified, report the highest-signal surfaces searched, the closest candidates and why they failed, the likely failure mode, and the single most useful missing clue.
What ships with it
2 files 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.
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.
- 10d ago First seen · 46 lines · 30 tokens per session scan A e1d70405b3d9
search-x is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 10d ago), licensed MIT. It adds 30 tokens to every session and 442 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…