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 swan-gtm/gtm-skills --skill researchgit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/research)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/research"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/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/swan-gtm/gtm-skills/research"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/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 | $0.00036 | $0.01501 |
| Opus 5 | $0.00018 | $0.00750 |
| Sonnet 5 | $0.00007 | $0.00300 |
| Haiku 4.5 | $0.00004 | $0.00150 |
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 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Research is target-driven and doesn't require org config to function — there's no state-hint paragraph and no Setup.md. The agent just routes to the right sub-page and runs.
Step 1 — Parse the ask, pick the sub-page
Route based on what the user is asking about. Load the sub-page via swan-get-skill.
| Ask shape | Sub-page |
|---|---|
| Generic company / one company / "what does X do" / "/research acme" | Company |
| Named person — "/research tom from acme", "tell me about Jane Doe" | Person |
| Mapping the people inside one account — buying committee, who to thread to | AccountTeam |
| How does the target sell / their GTM / pricing posture | GTMmotion |
| What's recent / news / signals / last-30-days | News |
| Domain-level / web traffic / SEO / digital footprint | Domain |
| Financial health / funding / revenue / runway / ownership | Financial |
| Tech stack only — what tools do they run | TechStack |
| Where the target talks about competitors / displacement signals | CompetitorMentions |
If the ask is ambiguous (e.g. just a company name with no further context), default to Company. If the ask explicitly chains multiple facets ("research acme — company plus the buying committee"), it's fine to load two sub-pages — but always pick a primary.
Step 2 — Pick the depth
Most asks want a one-paragraph answer; some want a dossier. Read the user's phrasing:
- "/research acme" / "what does acme do" → brief read (3–5 lines, the essentials).
- "deep brief on acme" / "full dossier" / pre-meeting prep with a VP+ → run the sub-page end-to-end.
- "quick — is acme an ICP fit" → micro-answer, one paragraph.
Default to brief. Scale up only when the user signals depth, or when the situation (board prep, founder intro, executive outreach) demands it. Over-researching when a sentence would do is the most common failure mode.
Step 3 — Load the sub-page and execute
The sub-page owns the procedure for its facet. Follow it.
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 · 109 lines · 36 tokens per session scan A 46927426e04d
research is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,501 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 2026-09-03.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…