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/heurema/herald/news-initgit clone --depth 1 https://github.com/heurema/heraldWrote 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/commands/heurema/herald/news-init)<a href="https://agentmods.dev/commands/heurema/herald/news-init"><img src="https://agentmods.dev/badge/commands/heurema/herald/news-init.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00519 |
| Opus 5 | $0.00005 | $0.00260 |
| Sonnet 5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
news-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are setting up the herald v2 daily news digest pipeline.
Steps
-
Check if already set up: Find the herald data directory by running:
cd "${CLAUDE_PLUGIN_ROOT}" && PYTHONPATH=. python3 -c "from herald.cli import _default_data_dir; print(_default_data_dir())"Check if
config.yamlexists in that directory (defaults to~/.local/share/herald/; falls back to~/.herald/for legacy installs; override with--data-dirorHERALD_DATA_DIR).- If it exists: tell user setup is done, offer to show status (
/news-status) or run pipeline (/news-run).
- If it exists: tell user setup is done, offer to show status (
-
Run init:
cd "${CLAUDE_PLUGIN_ROOT}" && PYTHONPATH=. python3 -m herald.cli init
-
Configure sources: Read
config.yamlfrom the herald data directory (see step 1) and help user add sources:- Ask: "What topics do you follow? (e.g., AI, Rust, DevOps, security)"
- Based on answer, suggest sources with RSS feeds and HN integration
- Edit the resolved data dir path
config.yaml(from step 1) to add sources using this format:sources: - id: hn name: Hacker News weight: 0.3 category: community - id: simonw name: Simon Willison url: https://simonwillison.net/atom/everything/ weight: 0.2 - For HN source, add
hnadapter mapping (handled by pipeline) - Optionally configure topics for keyword filtering
-
Run first collection:
cd "${CLAUDE_PLUGIN_ROOT}" && PYTHONPATH=. python3 -m herald.cli run
-
Show results: Report articles collected and stories created.
-
Privacy note: "All data stays local in your herald data directory (~/.local/share/herald/ by default). No paid API keys required. RSS feeds are fetched directly."
-
Next step: "Run
/news-digestto read today's digest."
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.
- 5d ago First seen · 53 lines · 9 tokens per session scan A e9912792937c
news-init is a command published in the GitHub repository heurema/herald (4 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 519 once invoked, about $0.0000 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
learn
Force claude-smart to extract learnings from this session now.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.