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/siddiqss/semantic-seo-suitenpx agentmods add skills/siddiqss/semantic-seo-suite/semantic-draft-writerWrote 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/siddiqss/semantic-seo-suite/semantic-draft-writer)<a href="https://agentmods.dev/skills/siddiqss/semantic-seo-suite/semantic-draft-writer"><img src="https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/semantic-draft-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/skills/siddiqss/semantic-seo-suite/semantic-draft-writer"><img src="https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/semantic-draft-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 | $0.00105 | $0.01347 |
| Opus 5 | $0.00053 | $0.00674 |
| Sonnet 5 | $0.00021 | $0.00269 |
| Haiku 4.5 | $0.00011 | $0.00135 |
Grade A, and why
semantic-draft-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 10d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
semantic-draft-writer
Turn a brief into publishable copy that is deep, specific, extractive, and — the part other tools skip — factually honest. "Passes the validator" is the floor, not the goal: the goal is a piece genuinely worth reading. The draft is done when it is fabrication-clean AND clears the quality bar (or its remaining gaps are explicitly surfaced).
Read first: ../../framework/semantic-writing-rules.md (especially the Craft & depth
rules 22–28), ../../framework/macro-micro-semantics.md. Load the brief, the node,
brands/<slug>/locked-facts.json, and entity-profile.json (for voice/audience).
Workflow
-
Scope depth and surface fact gaps FIRST. Before writing, list the concrete specifics a strong piece needs — real examples, named entities, figures, a point of view — and check them against
locked-facts.json+ the brief. If the piece can only be written generically because the facts aren't there, that is a signal to ask the user for the missing specifics (real customer result, actual feature names, a workflow detail) rather than writing vague filler. Thin facts are the #1 cause of thin drafts. -
Front-matter first. Emit the required block (semantic-writing-rules.md): node_id, target_query, intent, entities_covered, internal_links, schema_type, locked_facts_used (start empty), sources (start empty).
-
Draft for a reader, section by section along the brief's contextual vector. Lead a section with the extractive answer (rules 3–4) THEN go deep: mechanism, a concrete example (rule 23), a trade-off, a real point of view (rule 26). Do not turn every H2 into a tiny Q&A (rule 27) — vary the shape. Declarative, specific, filler-free.
-
Honour the locks while writing:
- State a brand fact ONLY if it exists in
locked-facts.json; when you use one, add its key tolocked_facts_used. - State an external factual number ONLY with a citation; add the URL to
sources. - Where a figure would help but isn't grounded, write the honest version (mechanism/
range/"depends on…") — never invent one. Pull from the brief's
do_not_fabricate.
- State a brand fact ONLY if it exists in
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 92 lines · 105 tokens per session scan A 0419f66bb4a0
semantic-draft-writer is a skill published in the GitHub repository siddiqss/semantic-seo-suite (9 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 1,347 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 skills, from other repositories
fire-your-seo-agency
A procedure for improving how a website appears in search engines and how AI answer systems find and cite it. It covers search, answer-engine, generative-AI, and Naver visibility.
geo-loop
Run one bounded eGEOagents loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, append one Timeline entry and one LOG line. Use for loop mode, /geo:loop, scheduled GEO runs, or continuous monitoring.
competitive-analysis
Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.
content-scoring
Score content against the 10 GEO criteria with evidence and prioritized fixes. Use when users ask to score, rate, evaluate, or estimate ranking strength.
schema-generator
Generate JSON-LD schema markup for pages and content types with an implementation checklist. Use when users ask for schema, structured data, rich snippets, or markup.
validation-doctor
Check Brave Search and Chrome DevTools MCP availability and provide exact setup snippets. Use when validation dependencies are missing or uncertain.