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.
npx agentmods add commands/vuvax/press-rank/writegit clone --depth 1 https://github.com/VUVAX/press-rankWhat 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 | $0.00015 | $0.00414 |
| Opus 5 | $0.00008 | $0.00207 |
| Sonnet 5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
write 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 2d 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.
What it actually says
/press:write
Write a complete, WordPress-ready draft optimized for both search ranking and AI citation.
Input
$ARGUMENTS— the topic. If a brief exists atresearch/<slug>.md, read and follow it. Otherwise generate a lightweight brief first.
Steps
- Load context. Read the research brief and any files under
context/(brand voice, target keywords, style guide) if present. - Structure for intent. Open with an answer-first introduction that resolves the query in the first 2–3 sentences (snippet + AI citation bait). Use H2/H3 headers that mirror real search questions.
- Integrate keywords naturally. Primary keyword in the H1, first 100 words,
one H2, and the conclusion. Secondary + semantic keywords distributed without
stuffing. (Delegate to the
keyword-mapperskill.) - GEO pass. Add quotable stats with sources, a short FAQ block, named
entities, and self-contained paragraphs an AI can lift verbatim. (Delegate to
geo-optimizer.) - WordPress front matter. Emit the frontmatter contract (see
CLAUDE.md) with title, slug, meta_title, meta_description, keywords, categories, tags, andstatus: draft.
Output
Save to drafts/<slug>.md. End by recommending:
Run /press:optimize drafts/<slug>.md, then /press:audit before publishing.
Quality bar
- Search intent matched, no keyword stuffing (density ≤ 2%).
- At least one snippet-target block (definition, list, or table).
- FAQ block with 3–5 real questions.
- Every claim that cites a number names its source.
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.
- 2d ago First seen · 40 lines · 15 tokens per session scan A 576a57f3364e
write is a command published in the GitHub repository VUVAX/press-rank (2 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 414 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
auto
Natural-language front door to the marketing pack (narrative/TALE, SEO/GEO/SITE, social/ECHO, email/SEND, Paid Ads/ROAS, influencer/STAR, launch/RAMP). Use when a marketing goal is open-ended or spans disciplines, when it is unclear which skill fits, or for requests like 'help with our marketing', 'grow our traffic'…
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.
narrative
Run a brand-narrative & messaging (TALE) workflow: trace the current message and positioning truth, architect the durable message house/voice/story canon, land it consistently across every surface, and evaluate resonance with tests and drift monitoring. 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.