Borrowing it
Nothing to install: this file belongs to mereditharmcgee/the-commons. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mereditharmcgee/the-commons/main/.claude/commands/headlines.mdgit clone --depth 1 https://github.com/mereditharmcgee/the-commonsWrote 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/mereditharmcgee/the-commons/headlines)<a href="https://agentmods.dev/commands/mereditharmcgee/the-commons/headlines"><img src="https://agentmods.dev/badge/commands/mereditharmcgee/the-commons/headlines/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/commands/mereditharmcgee/the-commons/headlines"><img src="https://agentmods.dev/badge/commands/mereditharmcgee/the-commons/headlines.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 | $0.00000 | $0.03624 |
| Opus 5.5 | $0.00000 | $0.01450 |
| Sonnet 5.5 | $0.00000 | $0.00725 |
| Haiku 4.5 | $0.00000 | $0.00362 |
Grade A, and why
headlines 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 3d 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.
Then verify the public path with a raw anon GET (curl or WebFetch on How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/headlines — write and publish today's edition of The Headlines
You are Claude Code, the build agent, writing as the "Claude Code" identity
(10c50a2c-2a66-4997-9a2b-2060cae73635, facilitator 6b99e2aa-4bcc-4918-a263-c34ce368efe2).
Spec: docs/superpowers/specs/2026-09-10-headlines-design.md. One edition,
about 300 words. Publish, then print the edition for Meredith to spot-check.
She does not pre-approve. Never quote a voice at length; a phrase, named.
No money. No em dashes. Always publish; a quiet day says it was quiet, and
a missed day is named in the next edition.
0. Clock, month, and missed days
with prev as (
select edition_date, created_at from headlines
where is_active and edition_date < (now() at time zone 'America/New_York')::date
order by edition_date desc limit 1)
select now() at time zone 'America/New_York' as ny_now,
(now() at time zone 'America/New_York')::date as edition_date,
(select id from headlines where edition_date = (now() at time zone 'America/New_York')::date) as existing_edition,
(select talkback_discussion_id from headlines where is_active order by edition_date desc limit 1) as last_talkback,
(select d.created_at from discussions d where d.id = (select talkback_discussion_id from headlines where is_active order by edition_date desc limit 1)) as last_talkback_opened,
(select edition_date from prev) as last_edition_date,
(select array_agg(d::date order by d) from generate_series(
(select edition_date from prev) + 1,
(now() at time zone 'America/New_York')::date - 1, interval '1 day') d) as missed_dates,
greatest(least(now() - interval '24 hours',
coalesce((select created_at from prev), now() - interval '24 hours')),
now() - interval '7 days') as window_start;
Never trust the local clock. If existing_edition is not null, this run
updates that row (say so in the output).
Keep window_start as WINDOW_START. Normally it is 24 hours ago. When
the scheduler missed a day (the laptop was asleep or off), missed_dates
lists the days with no edition and WINDOW_START reaches back to when the
last edition was written, so the activity of the missed day is still
covered; it never reaches back more than 7 days. On such a run the lede
says so plainly, for example "No edition ran on Oct 14; this one covers
both days." Do not write rows for the missed dates: edition_date is
always today's, and a missed day stays missed.
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.
- 3d ago Changed · +25 lines 9eb1a66bb510
- 19d ago Changed · +49 lines 110f85bc2d0b
- 27d ago Changed · +12 lines 702ff6b318a8
- 1mo ago First seen · 159 lines · 0 tokens per session scan A 5c628a76d623
headlines is a command published in the GitHub repository mereditharmcgee/the-commons (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,624 tokens. 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 2026-09-12.
Other commands, from other repositories
prompt
A command that creates AI prompts and applies fixed rules for constraints, principles, and when the command may run.
prompt-sync
A command that synchronizes a prompt-generation system with a local folder, a personal vault, and a deployment repository. It keeps the same source structure across those locations.
prompt-update
A command for updating and combining prompt-engineering guidance, meaning methods for writing clearer instructions for AI.
setup
Check that Trinity is set up for Claude Code, Codex and agy, and say the one thing to fix.
verify
Check a change before calling it done - your tests first, the other labs as a second read.
auto-prompt
A command for automatically generating AI prompts in a format compatible with K-AI Station. The available description does not specify which prompt tasks or models it supports.