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.
git clone --depth 1 https://github.com/prashishh/seo-geo-report-engineWrote 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/commands/prashishh/seo-geo-report-engine/competitor-watch)<a href="https://agentmods.dev/commands/prashishh/seo-geo-report-engine/competitor-watch"><img src="https://agentmods.dev/badge/commands/prashishh/seo-geo-report-engine/competitor-watch/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/commands/prashishh/seo-geo-report-engine/competitor-watch"><img src="https://agentmods.dev/badge/commands/prashishh/seo-geo-report-engine/competitor-watch.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 | $0.00019 | $0.01113 |
| Opus 5 | $0.00010 | $0.00557 |
| Sonnet 5 | $0.00004 | $0.00223 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
competitor-watch 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/competitor-watch [project]
Weekly competitor watch for $1 (defaults to the active project — resolve with
./bin/mkt config show). Pulls a fresh snapshot of each competitor, diffs it against the last
stored snapshot, and writes a dated brief of what changed plus recommended 48-hour responses.
This is the recurring companion to the one-time competitor-analysis skill; methodology and the
48-hour discipline live in playbooks/competitor-intel.md.
Steps
-
Load context.
./bin/mkt config show --project $1. Readclient.yml→ ourdomain,competitors[],market,ahrefs.project_id. If competitors are empty, stop and tell the user to populateclient.yml(or run thecompetitor-analysisskill first). -
Load the previous snapshot. Look in
projects/<client>/data/competitor-snapshots/. Use the most recentcompetitor-snapshot-<YYYY-MM-DD>.json. If none exists, this is the baseline run — capture the snapshot, note there's no diff yet, and skip to step 6. -
Pull current snapshots (Ahrefs MCP first —
knowledge/ahrefs-mcp-map.md). Per competitor domain capture:- Organic keywords —
site-explorer-organic-keywords→ store the top set so you can derive new and lost keywords next week (which terms moved into / out of top-10). - Referring domains —
site-explorer-referring-domains→ new ref domains this week. - Top pages —
site-explorer-top-pages/site-explorer-pages-by-traffic→ new or newly-surging pages (a page that wasn't there or jumped in traffic = a fresh content bet). - Domain Rating —
site-explorer-domain-rating→ DR change vs last snapshot. - Ads —
WebFetchthe Meta Ad Library (https://www.facebook.com/ads/library/) for each competitor → new active creatives / offers. Note new seasonal or discount pushes. - (Optional, if
ahrefs.project_idis set)rank-tracker-competitors-overviewfor tracked-term position moves against us.
- Organic keywords —
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 · 73 lines · 19 tokens per session scan A f0871ae8f67e
competitor-watch is a command published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 1,113 once invoked, about $0.0001 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 commands, from other repositories
seo-geo
SEO/GEO end-to-end along the SITE loop: survey demand and competitors, implement content, tune quality/tech/on-page, and evaluate authority/rankings/reports/memory (--phase survey|implement|tune|evaluate). Not sure? Use /aaron-marketing:auto.
ad
Run a paid-ads (ROAS) workflow: audience segments, account structure, ad creative, experiment design, pre-launch signal QA + the account-audit gate, measurement, and attribution. Not sure? Use /aaron-marketing:auto.
Run an email-marketing (SEND) workflow: deliverability/consent setup, segmentation, email creative, lifecycle flows, newsletter monetization, send-testing, and the email-quality audit gate. Not sure? Use /aaron-marketing:auto.
influencer
Run an influencer-marketing (STAR) workflow: audience & creator scouting, campaign targeting, briefs, outreach, amplification, and ROI reporting. Not sure? Use /aaron-marketing:auto.
launch
Run a product-launch (RAMP) workflow: positioning and launch tiering, window/early-access design, message house and asset kits, the launch-readiness gate with a T-1 go/no-go, launch-day execution, and the post-launch prove loop. Not sure? Use /aaron-marketing:auto.
narrative
Run a brand-narrative & messaging (TALE) workflow: trace the current message and positioning truth, architect the durable message house/voice/story canon, land it consistently across every surface, and evaluate resonance with tests and drift monitoring. Not sure? Use /aaron-marketing:auto.