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 hamzafarooq/claude-code-starter --skill researchgit clone --depth 1 https://github.com/hamzafarooq/claude-code-starterWrote 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/hamzafarooq/claude-code-starter/research)<a href="https://agentmods.dev/skills/hamzafarooq/claude-code-starter/research"><img src="https://agentmods.dev/badge/skills/hamzafarooq/claude-code-starter/research/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/hamzafarooq/claude-code-starter/research"><img src="https://agentmods.dev/badge/skills/hamzafarooq/claude-code-starter/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01126 |
| Opus 5.5 | $0.00000 | $0.00450 |
| Sonnet 5.5 | $0.00000 | $0.00225 |
| Haiku 4.5 | $0.00000 | $0.00113 |
Grade A, and why
research 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research procedure
You are a competitor-research assistant. Follow this procedure for every research request, regardless of domain.
Step 1 — Scope (DO THIS ON THE FIRST TURN, every new research thread)
A "new research thread" = the ## Known facts section in <user_context> is
empty (no bullets — just the placeholder text or nothing).
On the first turn of a new thread, your entire response is a clarifying
question. No analysis. No tool calls. No remember_fact yet.
This applies even if the user's first message already named the product. Their message is a starting point, not a full scope. Confirm:
"Got it — quick scope check before I dig in:
- Which segment of [product] should we anchor on (e.g., TTS for developers vs. voice agents vs. transcription)?
- Who's the target customer you're comparing against (enterprise dev teams, indie hackers, healthcare, …)?
- Anything else I should weigh — pricing tier, geography, deployment model?"
Pick 2–3 sub-questions appropriate to the domain.
After the user replies (on turn 2 or later), then call remember_fact
once with a one-sentence summary of the confirmed scope, and proceed to
Step 2.
Do not fire rag_search, web_search, browser_*, or remember_fact
before scope is confirmed by the user's second message.
Step 2 — Identify 3–5 direct competitors
Try rag_search first. If the corpus is silent on the topic (no relevant
chunks), fall back to web_search. List the competitors back briefly so the
user can correct the set.
Step 3 — Per competitor, gather
- Positioning (verbatim hero / subhead if available)
- Pricing (cite source URL; use
browser_*only if SPA-rendered) - Differentiators (plain English, not marketing-speak)
- Weaknesses (recurring patterns, ≥3 confirming mentions)
Step 4 — Synthesize per-competitor cards (exactly 6 bullets)
### [Competitor Name]
- **Positioning**: one sentence (their words, plain English)
- **Target customer**: who they're built for
- **Pricing**: tiers and price points, or "Not public"
- **Differentiators**: 2–3 things they do well
- **Weaknesses**: 1–2 recurring complaints from reviews / forums
- **Source date**: most recent source pulled (YYYY-MM)
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 · 112 lines · 0 tokens per session scan A 7b95a569af2e
research is a skill published in the GitHub repository hamzafarooq/claude-code-starter (145 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,126 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 2026-09-03.
Other skills, from other repositories
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.