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 competitor-monitoringgit 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/competitor-monitoring)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/competitor-monitoring"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/competitor-monitoring/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/competitor-monitoring"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/competitor-monitoring.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 | $0.00157 | $0.01741 |
| Opus 5 | $0.00078 | $0.00870 |
| Sonnet 5 | $0.00031 | $0.00348 |
| Haiku 4.5 | $0.00016 | $0.00174 |
Grade A, and why
competitor-monitoring 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor monitoring
Runs whenever someone needs a current read on the competitive landscape — on a cadence, before a strategy conversation, or the moment a rival's name comes up in a lost deal. Produces a dated, source-linked intelligence briefing of genuinely new competitor moves, plus an updated running memory per competitor so the next run starts where this one ended.
The failure mode this skill exists to prevent: a briefing that confidently reports last quarter's funding round as this week's news because a recap article was published yesterday. Everything below is built around one distinction — when a page was published vs. when the event actually happened — and a memory that remembers what you already reported.
Set up the profile (first run only)
- Ask for the company's website domain, then search the live web for the domain to confirm you have the right company. Confirm with the user before proceeding.
- Build the competitor list one of two ways: the user names them, or you propose them — run three parallel searches ("[Company] competitors", "[Company] vs", "[Company] alternatives"), synthesize a candidate list, and get explicit confirmation. Never research a competitor list the user hasn't approved.
- For each confirmed competitor, capture name, domain, and category (direct, adjacent, incumbent). Also capture 2–3 industry keywords for trend searches.
- Save all of this to a profile file in your workspace, alongside a
competitors/directory that will hold one running memory file per competitor and abriefings/directory for saved runs.
Pick the run mode
Check the profile's last-run date before searching anything:
- Full mode — first run, or last run more than 14 days ago. Search window: the past 14 days. Output: the full briefing.
- Quick refresh — last run within 14 days. Search window: since the last run, but never narrower than 7 days (too-narrow windows return empty results and read as false quiet). Output: the short delta format.
- Same-day repeat — a report already exists for today. Ask before re-running: "Already ran today — run again for fresh data?" Never silently re-run; it burns effort to produce a near-identical report.
What ships with it
3 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.
- 12d ago First seen · 86 lines · 157 tokens per session scan A b435686526d1
competitor-monitoring is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 157 tokens to every session and 1,741 once invoked, about $0.0008 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
a-b-testing
Design statistically sound GTM experiments for copy, channels, landing pages, sequencing, pricing, and funnel conversion. Produces hypothesis, sample-size logic, success metrics, test plan, analysis method, and scale/stop/kill recommendation. Use when planning A/B tests, split tests, or experiment roadmaps.
attribution
Build practical B2B attribution models across first touch, lead creation, opportunity creation, multi-touch, account-based influence, and sales-sourced revenue. Produces model comparison, UTM governance, source-of-truth rules, and channel ROI view. Use when marketing and sales disagree on source or ROI.
campaign-analytics
Analyze campaign performance from deliverability through revenue: delivery, engagement, replies, meetings, SQOs, pipeline, CAC, and payback. Produces diagnostic scorecard, root-cause analysis, benchmark comparison, and next-action plan. Use when deciding whether to scale, fix, or kill campaigns.
deliverability-monitoring
Monitor outbound deliverability health across domains, inboxes, DNS, bounces, spam placement, reply rates, and reputation signals. Produces alert thresholds, dashboard spec, weekly QA checklist, and remediation playbook. Use when inboxing drops, bounce rates rise, campaigns underperform, or new infrastructure launches.
gtm-metrics
Build a GTM metrics system for SaaS: funnel conversion, pipeline velocity, win rates, CAC, payback, NRR, sales efficiency, growth accounting, and executive dashboards. Use when creating metrics dashboards, board reports, revenue reviews, operating cadence, or diagnosing growth constraints.
tracking-plan
Master analytics tracking plan for PLG and B2B SaaS — unified event taxonomy, pixel strategy (1P and 3P tagging), marketing attribution architecture, CDP implementation (Segment, Rudderstack), product analytics (Amplitude, Mixpanel, PostHog), CRM tracking (HubSpot, Salesforce), and analytics infrastructure design. Use…