A workflow for creating a blog post or other content task from a topic. It sends the task through drafting, title checks, image creation, citations, and several quality-review stages.

Use it when someone asks for an article or post about a topic. It creates the task and runs it through the project's content-generation pipeline.

It removes the need to coordinate the many checks involved in preparing publishable content, including fact-checking, links, images, and consistency.

create-post — Skill for Claude Code and Codex by Glad-Labs

Install

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.

Any agent

npx skills add Glad-Labs/poindexter --skill create-post

Clone the repo

git clone --depth 1 https://github.com/Glad-Labs/poindexter

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/glad-labs/poindexter/create-post.svg)](https://agentmods.dev/skills/glad-labs/poindexter/create-post)

Your own site

<a href="https://agentmods.dev/skills/glad-labs/poindexter/create-post"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/create-post.svg" alt="Measured on agentmods" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,034 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.01034
Opus 5	$0.00020	$0.00517
Sonnet 5	$0.00008	$0.00207
Haiku 4.5	$0.00004	$0.00103

Measured 7d ago against content hash 1718d004fb4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

create-post 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/poindexter/create-post/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Post

Creates a new content task via POST /api/tasks. Pending tasks are dispatched by Prefect (services/flows/content_generation.py) and run through the canonical_blog pipeline — a 36-node graph_def stored in the pipeline_templates table (authored in services/canonical_blog_spec.py, compiled by services/pipeline_architect.py). The chain runs linearly through six blocks:

verify — verify_task: task record exists and is processable.
writer — generate_draft → generate_title → check_title_originality → normalize_draft → draft_gate (optional HITL, seeded off) → writer_self_review → resolve_internal_link_placeholders → reconcile_citations (deterministic citation repair, #765).
quality + images — quality_evaluation (pattern-QA gate) → url_validation → plan_image_markers → generate_images → inject_images → source_featured_image → caption_images (vision alt-text).
qa.* rail block (12 atoms) — qa.programmatic → qa.critic → qa.deepeval → qa.ragas → qa.vision → qa.topic_delivery → qa.citations → qa.unlinked_attribution → qa.consistency → qa.self_consistency → qa.web_factcheck → qa.aggregate: multi-model QA delegating to multi_model_qa.py; qa.aggregate makes the gate decision (halts on reject, no rewrite loop). Replaced the deleted cross_model_qa stage (#355).
seo + media — seo.generate_all_metadata (single structured call, #734) → generate_media_scripts → generate_video_shot_list → capture_training_data.
finalize — compile_meta → persist_task → record_pipeline_version → evaluate_auto_publish: mark awaiting_approval (or auto-publish if score ≥ threshold).

The writer model is DB-configurable via cost tiers (cost_tier.{free,budget,standard,premium}.model in app_settings), not hardcoded.

Tasks that fail QA are rejected — qa.aggregate halts the graph on reject (no automatic rewrite loop as of #355) and the post lands with a loud reason on the /pipeline dashboard.

Read the full file on GitHub · 63 lines

Files

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.

scripts/run.sh 1.3 KB runs code

Changes

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.

7d ago First seen · 63 lines · 41 tokens per session scan A 1718d004fb4e

Subscribe to this mod's changes

create-post is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 1,034 once invoked, about $0.0002 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.

Marketing and SEO Writing and docs ai ai-content automation blog-engine content-pipeline fastapi

spec-generate

Product Spec Builder that helps PMs generate clear, structured, testable PRDs. Creates both full and lightweight specs for any product or platform with a guided step-by-step workflow. Output in English Markdown format.

djblack1209-coder/OpenClaw-Bot · 46 tokens

product-team

A Chinese-language product development workflow led by one AI team lead taking several roles: product strategy, requirements writing, prototype creation, and user-experience review.

djblack1209-coder/OpenClaw-Bot · 104 tokens

Playwright (Automation + MCP + Scraper)

Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use when (1) you need a real browser, not static fetch; (2) the task involves Playwright MCP, browser tools, Playwright tests, scripts, or JS-rendered pages; (3) the…