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 account-research-briefgit 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/account-research-brief)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/account-research-brief"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/account-research-brief/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/account-research-brief"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/account-research-brief.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 | $0.00072 | $0.00716 |
| Opus 5 | $0.00036 | $0.00358 |
| Sonnet 5 | $0.00014 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
account-research-brief 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 12d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run this before a first meeting or an ABM push. It produces a one-page brief where every claim is tagged as evidence-backed or inference, so the AE knows what they can say out loud.
The play
-
Resolve the company to a stable identifier first. Match on the company's own URL slug rather than its display name. Name search returns near-matches and you will research the wrong entity, which is worse than researching nothing.
-
Pull firmographics. Size, industry, headquarters, founding year, description, specialities. This is the skeleton the rest hangs on.
-
Read composition, not just headcount. How the employee base splits by function and seniority says more than a total. A company that is 60% engineering sells differently than one that is 60% sales.
-
Extract positioning pillars. Cluster the company's own description, tagline, and specialities into three to six themes: product areas, target buyer, stated differentiators. Name each pillar and cite the exact source phrase. These are the words the buyer already uses about themselves.
-
Build a SWOT where every line is tagged. Mark each point
evidence(traceable to something retrieved) orinference(your read). An untagged SWOT is opinion wearing a suit, and an AE who repeats an inference as fact in a meeting loses the room. -
Ask before you spend on people. Confirm two things with the requester: which titles matter, and how many employee records to pull. Skipping this is how a routine brief turns into a surprise bill.
-
Read hiring as a live signal. Recent joiners, by function, are the most current evidence you have of where budget is moving. A team that added four engineers and no marketers last quarter is telling you something.
-
Deliver both shapes. Structured data for the next automation step, and a short human brief for the AE. They have different readers and different lifespans.
What good looks like
- The best briefs quote the company's own language back. Buyers relax when you describe them the way they describe themselves.
- The mediocre version is a reformatted About page: no composition, no signal, no tagging, and nothing an AE could not have read themselves in two minutes.
- Absence is a finding. "No leadership changes in twelve months" is real intelligence. Say it rather than padding the section.
- You know it is good when the AE walks in able to say which claims are sourced and which are your read, and never has to guess.
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.
- 12d ago First seen · 43 lines · 72 tokens per session scan A 6475710147e0
account-research-brief is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 716 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 2026-08-30.
Other skills, from other repositories
lead-researcher
Interactive research partner that produces comprehensive account briefs from a company name.
account-research
Deep-dive company research producing a 1-page account brief for sales teams.
fs-electric-studio
OpenDesign as an enterprise design platform: a buyer-forwardable proposal for a design-org's economic buyer — pain, value, ROI, rollout. Built as a decision-grade B2B sales deck for economic buyer, design VP, procurement.
huashu-bento-insight
OpenDesign vs closed cloud design tools: a side-by-side displacement case on control, cost (BYOK), and lock-in. Built as a decision-grade B2B sales deck for evaluation committee.
html-ppt-product-launch
OpenDesign Teams: a launch-and-adoption proposal for a mid-market design team weighing a switch from closed cloud tools. Built as a decision-grade B2B sales deck for design team lead, IT.
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.