A daily content workflow that gathers outside information, checks what matters, writes briefs and drafts, reviews their writing style, and delivers the results.

Use it to produce daily briefs and draft content from configured sources. It can also deliver output with notifications when the required tools are available.

It brings several content tasks into one repeatable run instead of requiring you to collect sources, assess them, write, edit, and send the results separately.

pipeline — Skill for Claude Code by ondrej-svec/heart-of-gold-toolkit

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 ondrej-svec/heart-of-gold-toolkit --skill pipeline

Clone the repo

git clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkit

Made for: Claude Code.

Or install guide, the plugin that ships this one along with the rest of its 7 skills.

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/ondrej-svec/heart-of-gold-toolkit/pipeline/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/pipeline)

Your own site

<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/pipeline"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/pipeline/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/pipeline"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,471 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00026	$0.05471
Opus 5.5	$0.00010	$0.02188
Sonnet 5.5	$0.00005	$0.01094
Haiku 4.5	$0.00003	$0.00547

Measured 2mo ago against content hash 41f3aee938d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pipeline 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 2mo 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.

- `jq` and `curl` on PATH

plugins/guide/skills/pipeline/SKILL.md · 442 lines

How it starts

The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/guide:pipeline — Daily Content Pipeline

"Time is an illusion. Lunchtime doubly so." — But your daily brief runs on schedule.

Run the full content pipeline: fetch signals, analyze relevance, create daily brief + drafts, edit for voice fidelity, and deliver output with notifications.

Prerequisites

content/config.yaml in the user's project (falls back to plugin defaults if missing)
Python 3.10+ with feedparser and pyyaml
jq and curl on PATH
Optional: gws CLI for Gmail, osascript for iMessage

Phase 0: Config Check

Before anything else, check if content/config.yaml exists.

If it exists: Read it and proceed to Phase 1.
If it doesn't exist: Tell the user: "No config found. Run /guide:setup to configure your content pipeline — it takes about 2 minutes and I'll walk you through it." Then stop. Do NOT use the defaults config as a silent fallback for a first run — the user needs to configure their own sources and themes.

Phase 1: Scout (Fetch Sources)

Run the pipeline fetch script to gather all external signals deterministically.

Finding Scripts

The fetch scripts live in this plugin's scripts/ directory. Determine the scripts path:

If this plugin is at heart-of-gold-toolkit/plugins/guide/, use heart-of-gold-toolkit/plugins/guide/scripts/
If installed via marketplace, use the plugin installation path's scripts/ directory
Locate by searching for fetch-rss.py in the project tree if unsure

Steps

Read config from content/config.yaml
Read voice reference from the path in voice.reference config field
Run the pipeline fetcher — a single deterministic script that calls ALL configured sources (RSS, Gmail, HN, Events/iCal), combines them, normalizes scores, and writes output:
```
bash <scripts>/run-pipeline-fetch.sh --config content/config.yaml
```
This script:
- Calls each enabled source (fetch-rss.py, fetch-gmail.sh, fetch-hn.sh, fetch-events.py)
- Combines all signals into a single array
- Normalizes scores to 0.0-1.0 with source weight multipliers applied
- Writes content/pipeline/YYYY-MM-DD/signals.json (with collision avoidance: signals-2.json, etc.)
- Writes content/pipeline/YYYY-MM-DD/fetch-log.json with per-source status
- Do NOT run individual fetch scripts yourself. The runner handles all of them.
Read signals.json from the pipeline directory — this is your input for Phase 2
Read fetch-log.json — check which sources succeeded/failed. If a source failed, mention it in the brief footer.
Read captures from content/captures/ (or configured captures_dir) — last 7 days of AM/PM captures
Read recent daily briefs — last 3 briefs from content/daily/ for deduplication context

Read the full file on GitHub · 442 lines

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.

2mo ago First seen · 442 lines · 26 tokens per session scan A 41f3aee938d9

Subscribe to this mod's changes

pipeline is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 5,471 once invoked, about $0.0001 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 2026-08-30.

Marketing and SEO Writing and docs

pipeline next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pipelineondrej-svec/heart-of-gold-toolkit	Skill	19	1mo ago	MIT	A	26	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

pipeline