news-sources

news-sources is a command for Claude Code from heurema/herald. It costs 11 tokens per session (403 once invoked), scanned A, original, MIT.

A command for viewing and changing the news sources configured for Herald. Herald is a news collection tool that groups sources by category and topic.

In plain words
What is it for?
Use it to list sources or remove one by name or ID from the configuration.
Why use it?
It gives you one place to see which feeds are used and remove sources that are no longer relevant.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the herald plugin — 1 skill, 7 commands, 1 hook shipped together

Good fit Use it to list sources or remove one by name or ID from the configuration.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add heurema/herald
Claude Code
/plugin install herald

Made for: Claude Code.

Or install herald, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 1 hook.

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.

agentmods badge for news-sources

README.md
[![agentmods](https://agentmods.dev/badge/commands/heurema/herald/news-sources/github.svg)](https://agentmods.dev/commands/heurema/herald/news-sources)
Your own site
<a href="https://agentmods.dev/commands/heurema/herald/news-sources"><img src="https://agentmods.dev/badge/commands/heurema/herald/news-sources/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.

agentmods 80×15 button for news-sources

Your own site · 80×15
<a href="https://agentmods.dev/commands/heurema/herald/news-sources"><img src="https://agentmods.dev/badge/commands/heurema/herald/news-sources.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.00403
Opus 5 $0.00005 $0.00201
Sonnet 5 $0.00002 $0.00081
Haiku 4.5 $0.00001 $0.00040

Measured 10d ago against content hash 0054d614abe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

news-sources 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.

commands/news-sources.md · 52 lines

What it actually says

You are showing and managing the user's herald sources.

Preflight

  1. Find the herald data directory:
    cd "${CLAUDE_PLUGIN_ROOT}" && PYTHONPATH=. python3 -c "from herald.cli import _default_data_dir; print(_default_data_dir())"
    
    Check config.yaml exists there (defaults to ~/.local/share/herald/; use --data-dir or HERALD_DATA_DIR to override). If not: "Run /news-init first."
  2. Read config. If YAML parse fails: "Config file has invalid YAML."

Default: show all sources

  1. Read config.yaml from the herald data directory (see Preflight)
  2. Display sources grouped by category:
Sources:
  community:
    - hn: Hacker News (weight: 0.3)
  official:
    - openai: OpenAI Blog (weight: 0.25)

Topics: ai_agents, ai_models
Total: N sources
  1. Show available commands:
    • /news-add <url> — add a source
    • /news-sources remove <name> — remove a source

Subcommand: remove

  1. Read config
  2. Find source by id or name (case-insensitive match)
  3. If found: remove from sources list, write config via Edit tool
  4. Confirm: "Removed . Run /news-run to update."
  5. If not found: "Source '' not found. Run /news-sources to see all."

Config rules

  • Only edit the config.yaml in the herald data directory (see Preflight)
  • Use Edit tool for targeted changes
  • Preserve YAML comments
  • Always confirm before writing
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.

  1. 10d ago First seen · 52 lines · 11 tokens per session scan A 0054d614abe0

Subscribe to this mod's changes

news-sources is a command published in the GitHub repository heurema/herald (4 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 403 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.