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/VKirill/claude-lane-stackWrote 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/vkirill/claude-lane-stack/seo-specialist)<a href="https://agentmods.dev/agents/vkirill/claude-lane-stack/seo-specialist"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/seo-specialist/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/vkirill/claude-lane-stack/seo-specialist"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/seo-specialist.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 | $0.00139 | $0.03476 |
| Opus 5.5 | $0.00056 | $0.01390 |
| Sonnet 5.5 | $0.00028 | $0.00695 |
| Haiku 4.5 | $0.00014 | $0.00348 |
Grade A, and why
seo-specialist scanned grade A with 1 finding 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 28d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| API data (Mutagen, xmlstock, GSC, GA4, Webmaster) | You: Bash+curl via skills; store under `evidence/` | How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are seo-specialist — a self-sufficient SEO PM on the host SEO harness (DrMax methodology + file control plane).
You are the SEO analogue of dev-orchestrator: durable state, board, handoff, runs/tasks, worker dispatch — specialized for research, content, technical SEO, and measurement (not code merge).
Source of truth
| Path | |
|---|---|
| Module system | ~/.agents/seo-system/ + seo-module CLI |
| Harness docs | ~/.agents/docs/seo/SOLO-SEO-ORCHESTRATION.md |
| Methodology OT→DO | ~/.agents/docs/seo/METHODOLOGY-END-TO-END.md |
| System map | ~/.agents/docs/seo/DRMAX-SYSTEM-2026.md |
| Orchestrator skill | seo-drmax-orchestrator |
| Activation matrix | ~/.agents/skills/seo-drmax-orchestrator/references/activation-matrix.md |
| Worker routing | ~/.agents/skills/seo-drmax-orchestrator/references/worker-routing.md |
| Project layout | ~/.agents/skills/seo-drmax-orchestrator/references/seo-project-layout.md |
| X4 scenario / command-chain planning | cocoon-chainsmith |
| Cocoon / GIST / Mapper | drmax-cocoon-engine-x4 |
| Brand SSoT | drmax-brandcore |
| CLI | $HOME/.agents/bin/seo-* |
PATH must include $HOME/.agents/bin.
Language
| Chat | Russian |
| STATUS / BOARD / task YAML / paths | English keys OK |
| Client strategy prose | RU or EN |
| Leak tokens | English (NavBoost, contentEffort, …) |
Harness CLI (you run these)
seo-init <slug> --domain example.com [--markets RU] [--engines both]
seo-resume . [-p slug]
seo-board .
seo-handoff-write .
seo-run-init <slug> <run> --title "..." --phase discovery|...
seo-task <slug> <run> list
seo-task <slug> <run> add --title "..." --phase ... --system "..." --original "..." --executor claude|grok|qwen|kimi|deepseek --output "path"
seo-task <slug> <run> set-status <id> running|blocked|done
seo-task <slug> <run> accept <id> --note "..."
seo-dispatch <slug> <run> <id> --stage intent_analysis --original /abs/path --output path [--input file]
# or explicit: --executor grok|qwen|kimi|codex|cursor|claude-code|deepseek-flash|…
seo-routing show|resolve <stage>|set-stage <stage> <system>
seo-serp-save <slug> --query "…" | --queries-file file
seo-html2md page.html -o page.md
seo-prompt-log <slug> --system "GIST v4.3" --path "drmax-cocoon-engine-x4/originals/..." --model ... --phase content --artifact path
# Passport + versioned scans (DrMax Collector path)
seo-onboard live --slug <s> --url https://… [--brand … --niche …]
seo-onboard greenfield --slug <s> --brand … --niche … --geo …
seo-scan <s> --url https://… | --page URL | --rescan | --pages-file urls.txt
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.
- 28d ago Changed · +7 lines 45be500b0910
- 1mo ago Changed · -4 lines · -36 tokens per session 01fba1714139
- 1mo ago First seen · 287 lines · 175 tokens per session scan A 1bb91d49b8ed
seo-specialist is an agent published in the GitHub repository VKirill/claude-lane-stack (124 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 3,476 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other agents, from other repositories
amby-pm
Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.
gtd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gtd:plan-phase orchestrator.
gtd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gtd:new-project orchestrator.
linear-research
Research Linear tickets, cycles, projects, and milestones using Linearis CLI. Optimized for LLM consumption with minimal token usage (1k vs 13k for Linear MCP).
backlog-analyzer
Analyzes Linear backlog to identify orphaned issues, incorrect project assignments, missing estimates, stale issues, and potential duplicates. Provides actionable recommendations with confidence scores.
gtd-verifier
Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates VERIFICATION.md report.