Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/prashishh/seo-geo-report-enginenpx agentmods add commands/prashishh/seo-geo-report-engine/client-reportWrote 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/client-report)<a href="https://agentmods.dev/commands/prashishh/seo-geo-report-engine/client-report"><img src="https://agentmods.dev/badge/commands/prashishh/seo-geo-report-engine/client-report.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01492 |
| Opus 5 | $0.00014 | $0.00746 |
| Sonnet 5 | $0.00005 | $0.00298 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
client-report 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 7d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/client-report
The one runner that turns a prospect URL into a branded, wow-grade pitch PDF, the same shape every time.
It orchestrates the first-scan-report skill's pipeline plus the competitive-research pass. The report
is the hook that wins the client: where they stand, who is beating them, where the open ground is, and
the plan. Client copy names competitors + real numbers (no vague euphemisms) and never names the
underlying tools/APIs (use neutral source labels like "live search data", "public review data").
Steps
-
Seed the project.
WebFetchthe prospect's site (product, ICP, positioning, named products, customers, socials). Createprojects/<slug>/client.yml:client_name,domain,competitors([{name, domain}] — the real funded peer set, verify domains),target_keywords(buyer terms across every product line),market,messaging.lanes, andsocial.linkedin(company-page URLs for the client + each rival, for the social benchmark). US/Labs market unlocks the full toolset. -
Run the live scan (each writes an artifact
first_scan.pyreads; US location code 2840):python3 tools/seo/authority.py --project <slug> --out projects/<slug>/data/raw/dataforseo/authority-<date>.json python3 tools/seo/keyword_research.py --project <slug> --location 2840 --seeds "..." --topic <core tokens> \ --out projects/<slug>/data/raw/dataforseo/kw-<date>.json python3 tools/seo/competitor_gap.py --project <slug> --location 2840 --topic <core tokens> \ --out projects/<slug>/data/raw/dataforseo/competitor-gap-<date>.json python3 tools/seo/opportunity_score.py --project <slug> --location 2840 --fit <core tokens> python3 tools/geo/llm_visibility.py --project <slug> --location 2840 --brand "Name" name.com \ --prompts "<8 buyer questions>" --out projects/<slug>/data/raw/dataforseo/ai-matrix-<date>.json python3 tools/seo/top_pages.py --project <slug> --location <code> --per 6 # what content each rival wins with python3 tools/seo/backlinks.py --project <slug> # backlink profile (ref domains, spam) + link-GAP outreach list (location-agnostic) python3 tools/seo/competitor_momentum.py --project <slug> # PredictLeads funding + hiring + news (SaaS/funded set; skip for local SMB) python3 tools/seo/google_ads.py --project <slug> --location <code> # Google Ads Transparency counts # --location = the client's market code (US 2840, Australia 2036). Same code for reputation + ads. python3 tools/seo/social_footprint.py --project <slug> # LinkedIn follower gap (needs social.linkedin) python3 tools/seo/web_vitals_bench.py --project <slug> # Core Web Vitals vs rivals (DataForSEO Lighthouse, no Google key) python3 tools/seo/reputation.py --project <slug> --location <code> # ratings (Google Business + G2/Trustpilot) + mined complaint themes = switching wedge python3 tools/seo/share_of_search.py --project <slug> # branded-demand momentum (Google Trends, leading indicator) python3 tools/seo/ad_messaging.py --project <slug> # what rivals say in their ads (messaging teardown)
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.
- 7d ago First seen · 77 lines · 27 tokens per session scan A af227dc675fc
client-report is a command published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 1,492 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
visibly-seo-pdf-build
Build a brand-compliant PDF from a Python script.
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.