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 skills/prashishh/seo-geo-report-engine/agency-dashboardWrote 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/prashishh/seo-geo-report-engine/agency-dashboard)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/agency-dashboard"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/agency-dashboard/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/prashishh/seo-geo-report-engine/agency-dashboard"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/agency-dashboard.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 | $0.00076 | $0.01077 |
| Opus 5 | $0.00038 | $0.00539 |
| Sonnet 5 | $0.00015 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
agency-dashboard 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 11d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agency-dashboard
A live operating console for the framework and its client projects, built to be worked from instead of Claude Code once a project is underway. Everything renders from project files on every request — never hand-maintain status in HTML.
Command
./bin/mkt dashboard serve # live server, opens the browser; re-reads files on refresh
./bin/mkt dashboard build # static export to projects/_dashboard/ (no server needed)
Prefer serve — it's a real HTTP server (tools/dashboard/build.py's _Handler), so adding a
skill, a project, or a file shows up on the next refresh with zero rebuild step. build is for a
portable snapshot (e.g. to hand someone a folder of static HTML).
What It Reads
skills/*/SKILL.md,commands/*.md,agents/*.md,playbooks/*.md,tools/*/— the live capability inventory (grouped, described in plain English, each one clickable for detail).projects/*/client.ymlfor client identity, domain, ICP, competitors, keywords, Ahrefs ids, messaging one-liner.projects/*/BUILD-STATUS.mdfor human-written status and blockers.research/,deliverables/,inputs/, anddata/inventories, with file mtimes for the recent-activity feed.- HTML deliverables for placeholder counts:
{{TODO}},[NEEDS...],[AUTHOR:],[unverified], and[confirm client may display].
Pages
- Overview — portfolio snapshot (projects, pages drafted, research artifacts, skills, tracking configured, handoff review items), a delivery-stage pipeline, a "needs attention" panel, a recent-activity feed, the capability layer summary, and project cards.
- Capabilities — the five-layer explainer (workflows/skills/agents/tools/playbooks) plus every skill grouped by area; click any skill or playbook for its own detail page.
- Per-project — stage/health/handoff pills, a completion ring, a headline quote (the client's
messaging one-liner), the rendered
BUILD-STATUS.md, and every artifact grouped strategy-first (inputs → research & strategy → schema/specs → pages produced → other deliverables → tracking data) with the built pages last, since that's execution output, not the thinking. - In-console viewers — every file type opens inside the console, not a raw tab: markdown renders as formatted text, CSV as a table, JSON pretty-printed, and built HTML pages render in an embedded preview frame (with an "Open full page" escape hatch).
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.
- 11d ago First seen · 91 lines · 76 tokens per session scan A cdf70b1233bd
agency-dashboard is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,077 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 2026-08-31.
Other skills, from other repositories
content-amplifier
Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…
email-sequence-designer
Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound sequence"; produces general lifecycle automation flows (welcome, cart, browse-abandon, post-purchase, in-flow re-engagement, B2B cold outbound)…
reactivation-specialist
Use when the user asks to "build a win-back campaign", "re-engage lapsed subscribers", "run a re-permission / re-consent sweep", or "sunset my dead list"; produces a closed-loop reactivation program — a lapsed-cohort definition, a staged offer ladder, a re-consent (re-permission) capture step, and a sunset-confirm /…
campaign-planner
Use when the user asks to "plan an influencer campaign", "build a campaign blueprint", "track or close a creator campaign", or "record a late campaign correction"; produces the plan and, when requested, a non-canonical evidence tracker with scoped identity, publication, reconciliation, close, and reopen receipts. Not…
product-feed-optimizer
Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price…
cold-outbound-sequencer
Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a…