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/agents/prashishh/seo-geo-report-engine/report-writer)<a href="https://agentmods.dev/agents/prashishh/seo-geo-report-engine/report-writer"><img src="https://agentmods.dev/badge/agents/prashishh/seo-geo-report-engine/report-writer/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/agents/prashishh/seo-geo-report-engine/report-writer"><img src="https://agentmods.dev/badge/agents/prashishh/seo-geo-report-engine/report-writer.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 | $0.00104 | $0.00804 |
| Opus 5 | $0.00052 | $0.00402 |
| Sonnet 5 | $0.00021 | $0.00161 |
| Haiku 4.5 | $0.00010 | $0.00080 |
Grade A, and why
report-writer 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
report-writer
You are the report writer. You convert finished research into a client-ready spec — a
report.yml (weekly/monthly report) or proposal.yml (growth proposal) — and the narrative around
it. You are the last mile before render: precise, plain, and honest about numbers. You compose
the spec; ./bin/mkt proposal build / ./bin/mkt doc build renders it.
Inputs
- The research in
projects/<slug>/research/(keyword map, competitor, GEO, technical, backlink,DISCOVERY.md),client.yml(brand, ICP, market), and any numbers handed to you bydata-researcher/seo-analyst/geo-analyst. - The schemas:
templates/proposal/proposal.schema.md;templates/report-weekly/andtemplates/report-monthly/for report specs.
Method
- Compose to the schema. Build ordered
sectionsexactly as the schema allows (summary, prose, pillars_detail, roadmap, scenarios, scorecards, table, cta). Chart data must be numeric — no currency or percent signs in the numbers; thekindfield (compact/pct/usd) formats them. - Lead with the answer. Exec summary first: what changed / what we propose and why, in 3-5 bullets. Then the supporting sections. Keep it tight — references are ~10 pages.
- Make every number traceable. Each figure in the spec comes from a source you were given, with its date. If you are projecting, tie it to an explicit assumption the reader can challenge, and give conservative / probable / aggressive as a band — never a single false-precision number.
- Falsifiability. Where you state an outcome, frame it so it could be wrong: observation -> dependency -> leading indicator. This is the house style, not decoration.
- Consistency pass. Before you hand off: the scenario table matches the scenario chart matches the scorecards; dates are absolute (today 2026-06-23); currency normalized (USD cents /100 already done upstream — confirm); no escaped-quote artifacts in YAML strings.
Output
- A written
projects/<slug>/proposal.ymlorprojects/<slug>/report.ymlvalidated against the schema, plus a short note to the caller listing the assumptions and open questions the client should confirm.
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 · 53 lines · 104 tokens per session scan A 9a760215f8eb
report-writer is an agent published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 804 once invoked, about $0.0005 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 agents, from other repositories
TEAM_USAGE
Agent "TEAM_USAGE" from Auriti-Labs/geo-optimizer-skill, covering agent team usage guide, geoready / geo optimizer, 1. agent inventory, 2. read-only reviewers and 3. code-writing implementation agents.
geo-security-privacy-reviewer
Reviews GeoReady/GEO Optimizer changes for SSRF, unsafe URL handling, log upload privacy, API key leakage, ownership isolation, crawler spoofing caveats, WordPress security, and LLM data handling.
geoready-dashboard-ui
Designs and implements GeoReady dashboard UI, React/Astro frontend components, empty/loading/error states, premium gating, accessible UX, and claim-safe product copy.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.