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 LiozShor/claude-code-skills --skill tech-researchergit clone --depth 1 https://github.com/LiozShor/claude-code-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/liozshor/claude-code-skills/tech-researcher)<a href="https://agentmods.dev/skills/liozshor/claude-code-skills/tech-researcher"><img src="https://agentmods.dev/badge/skills/liozshor/claude-code-skills/tech-researcher/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/liozshor/claude-code-skills/tech-researcher"><img src="https://agentmods.dev/badge/skills/liozshor/claude-code-skills/tech-researcher.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 | $0.00078 | $0.02561 |
| Opus 5 | $0.00039 | $0.01281 |
| Sonnet 5 | $0.00016 | $0.00512 |
| Haiku 4.5 | $0.00008 | $0.00256 |
Grade A, and why
tech-researcher 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 9d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Researcher
Use this skill when the agent needs current technical information before giving advice, writing implementation plans, choosing tools, or editing code.
The purpose of this skill is to prevent stale, confident, outdated technical recommendations. Many technical domains change quickly. A model may remember an old API, deprecated library, renamed package, outdated best practice, or abandoned framework. This skill forces the agent to verify current information before making a recommendation.
It uses the research MCP (Tavily/Exa/Firecrawl) tools (the same tooling pattern as /design-log Phase B) — built-in WebSearch/WebFetch are intentionally not in allowed-tools because these MCPs return full-page markdown and support parallel batch fetches, which is what this skill needs for primary-source verification.
When this triggers
Use this skill when the user asks about:
- The best current way to implement something.
- Which library, framework, package, API, SDK, tool, or platform to use.
- Direction decisions: pivoting an approach, build-vs-buy, replacing part of the stack, "what's the best thing to implement X with" — run these in decision-grade mode (below).
- Whether a package or framework is still maintained; current setup, syntax, APIs, or version-specific behavior.
- Technical architecture choices; comparing tools before implementation.
- Fast-moving domains: AI/ML tooling, agent frameworks, RAG, MCP, LLM SDKs, JS/TS frameworks, Python tooling, cloud platforms, CI/CD, databases, auth, deployment.
- Debugging that may depend on current package versions or changed APIs.
Trigger phrases: "what is the best way to…", "which library/tool should I use", "is this still recommended / maintained / deprecated?", "latest version", "current best practice", "compare these", "should I use X or Y?", "should I switch to…", "before implementing".
When this does not trigger
Do not use this skill when:
- The question is basic and stable, or purely conceptual with no implementation impact.
- The user explicitly asks not to search or not to verify externally.
- The task is only formatting, rewriting, translating, or summarizing user-provided text/docs.
- The answer can be safely handled from the project's existing local files.
- The user is already inside a
/design-logPhase B run — that workflow already handles research and this skill would duplicate it (but both share the same research index — see step 2).
What ships with it
9 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.
- 9d ago First seen · 133 lines · 78 tokens per session scan A b9c53019e2fd
tech-researcher is a skill published in the GitHub repository LiozShor/claude-code-skills (2 stars, last pushed 21d ago), licensed MIT. It adds 78 tokens to every session and 2,561 once invoked, about $0.0004 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…