Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/pramoddutta/botskills/publish-seo-batch)<a href="https://agentmods.dev/skills/pramoddutta/botskills/publish-seo-batch"><img src="https://agentmods.dev/badge/skills/pramoddutta/botskills/publish-seo-batch.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 | $0.00059 | $0.01225 |
| Opus 5 | $0.00030 | $0.00613 |
| Sonnet 5 | $0.00012 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
publish-seo-batch scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
echo "$s $(curl -s -o /dev/null -w '%{http_code}' https://botskills.sh/blog/$s)" How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish SEO Batch (botskills.sh)
Pipeline: source topics -> dedup slugs -> write -> gate -> relink -> register -> build -> commit -> deploy -> prove live -> IndexNow. A batch is not published until step 9 passes. Adapted from the qaskills.sh pipeline, which is the proven version of this.
Step 0: State check
git -C /Users/promode/botskills status --short # pre-existing WIP is not yours
date +%F # today, used in every post
Step 1: Source topics
docs/seo/topics-100.json holds the plan. Anything already written is a file in
packages/web/src/app/blog/posts/. Take the next unwritten topics from the plan,
or WebSearch for net-new demand. Topics mined from social posts go in the
x-signal cluster with a note that their facts are DISPUTED and need
verification.
Step 2: Dedup every slug BEFORE writing
cd /Users/promode/botskills
for s in slug-one slug-two; do
echo "$s: $(grep -rln "$s" packages/web/src/app/blog/posts/ | wc -l) hits"
done
Any hit means pick a different slug.
Step 3: Write
File packages/web/src/app/blog/posts/<slug>.ts, shape per
docs/seo/WRITER-SPEC.md. Depth per docs/seo/LONGFORM-SPEC.md:
3000-4000 body words, 13-15 declarative verb-led H2 sections, 4+ tables,
exactly 4 FAQ questions as the last H2.
Product facts come ONLY from docs/seo/VERIFIED-FACTS-2026-08-25.md. Nothing
from its DO NOT ASSERT list, ever. Grok Bot ships weekly and the popular posts
about it contradict each other, so re-verify against docs.x.ai before asserting
anything new. Every docs.x.ai page has a raw markdown twin at <path>.md.
Cluster addenda for templated title frames live in /tmp during a run and
should be recreated per batch: jobs, integrations, roles, and comparisons each
have anti-template rules, because a templated body gets the whole cluster
filtered out of the index.
Step 4: Gate every file
python3 /tmp/gate.py <slug>... # words, H2, tables, FAQ, desc, links, em dashes
python3 /tmp/checkh2.py <slug>... # H2 collisions against the whole corpus, must be 0
python3 /tmp/slop.py # banned phrases, opener uniqueness, prose duplication
python3 /tmp/seoaudit.py # titles, descriptions, orphans, broken links
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.
- 8d ago First seen · 130 lines · 59 tokens per session scan A 3db0e457a10d
publish-seo-batch is a skill published in the GitHub repository PramodDutta/botskills (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,225 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
hyperliquid-orders
Place, cancel and modify Hyperliquid orders correctly from the desk computer - limit and IOC (market-style) orders, take-profit and stop-loss trigger orders with grouping, client order ids, reduce-only, batch actions, price and size rounding, and how to read every response status. Write path - Execution Trader only…
desk-risk-limits
How the Risk Manager writes the desk's risk limits with the user, sizes every proposed trade from live account state and Hyperliquid's real constraints, checks the book, and issues a PASS or REJECT with exact ticket fields. Use for setting up or changing limits, sizing any trade, and answering "how's the book".
desk-strategy-lab
How the Strategist works with the user to turn their own trading idea into explicit rules, backtest it honestly on Hyperliquid candle and funding history, and paper-trade it on testnet through the desk lifecycle. Method only - the desk ships no strategies and makes no return claims. Use when the user wants to design…
hyperliquid-advanced
Less common Hyperliquid actions and their rules - dead-man's switch (scheduleCancel), TWAP orders, spot orders, expiresAfter and nonces, API wallet approval from code, sub-account and vault addressing, HIP-3 dexs, and what the desk deliberately does not do (transfers, withdrawals, builder fees, staking). Write actions…
desk-incident-response
What the desk does when something goes wrong on Hyperliquid - unknown send results, unexpected fills or positions, unprotected positions, stuck or orphaned orders, API outages, rate limiting, and suspected API wallet compromise. Contain first, reconcile from the exchange record, act only through approved tickets, then…
desk-operating-model
How the HyperGrok trading desk works as a team of Grok Bots - roles, seats, shared workspace, evidence standard, approval model and handoff format. Use when setting up the desk, when a Bot is unsure who owns something, or when a request does not fit the normal trade lifecycle.