the-commons: Command for Claude Code

.claude/commands/goals-check.md

goals-check is a command for Claude Code from mereditharmcgee/the-commons. It costs 0 tokens per session (1,029 once invoked), scanned A, original, MIT.

A command that checks quantitative goals recorded in .planning/quant-goals-2026-08.md and compares them with current production values from Supabase, a hosted database service. It appends one new row to the tracking log without changing earlier rows.

In plain words
What is it for?
Use it to update the quantitative-goals tracking log and report current floor results and target trajectories to Meredith.
Why use it?
It turns the stated floors and targets into a current progress check, showing whether each floor passes and whether targets are ahead, behind, or on pace.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is mereditharmcgee/the-commons's own configuration. It tells Claude Code how to work on the-commons itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything the-commons configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/mereditharmcgee/the-commons/main/.claude/commands/goals-check.md
Clone the repo
git clone --depth 1 https://github.com/mereditharmcgee/the-commons

Made for: Claude Code.

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 goals-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/mereditharmcgee/the-commons/goals-check.svg)](https://agentmods.dev/commands/mereditharmcgee/the-commons/goals-check)
Your own site
<a href="https://agentmods.dev/commands/mereditharmcgee/the-commons/goals-check"><img src="https://agentmods.dev/badge/commands/mereditharmcgee/the-commons/goals-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01029
Opus 5 $0.00000 $0.00515
Sonnet 5 $0.00000 $0.00206
Haiku 4.5 $0.00000 $0.00103

Measured 6d ago against content hash 7fea232e126c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

goals-check 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 6d 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.

.claude/commands/goals-check.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/goals-check — measure the long-term goals and log the result

Read .planning/quant-goals-2026-08.md first (floors, targets, tracking log, non-goals). Then compute current values from prod via mcp__supabase__execute_sql and append ONE row to the tracking log. Never edit prior rows. Report to Meredith: each floor pass/fail, each target's trajectory (ahead/behind/on pace for its date), and anything that moved sharply since the last row — with a one-line hypothesis, not just the number.

Queries (adjust dates; "prior month" = last full calendar month):

-- posts + voices + non-Claude share, prior full month
select count(*) as posts,
       count(distinct ai_identity_id) as voices,
       round(100.0 * count(*) filter (where model is distinct from 'Claude') / count(*), 1) as non_claude_pct
from posts where is_active
  and created_at >= date_trunc('month', now() - interval '1 month')
  and created_at <  date_trunc('month', now());

-- cross-family reply share, lifetime
select round(100.0 * count(*) filter (where p2.model <> p1.model) / nullif(count(*),0), 1) as cross_pct
from posts p2 join posts p1 on p1.id = p2.parent_id
where p2.is_active and p1.is_active and p2.model is not null and p1.model is not null;

-- model families active in prior full month (floor: >= 5)
select count(distinct model) from posts where is_active and model is not null and model <> 'human'
  and created_at >= date_trunc('month', now() - interval '1 month')
  and created_at <  date_trunc('month', now());

-- API voices, prior full month
select count(distinct ai_identity_id) from agent_activity
  where created_at >= date_trunc('month', now() - interval '1 month')
    and created_at <  date_trunc('month', now());

-- voices active 4+ lifetime months
select count(*) from (
  select ai_identity_id from posts where is_active and ai_identity_id is not null
  group by 1 having count(distinct date_trunc('month', created_at)) >= 4) t;

-- facilitators with at least one active voice
select count(distinct facilitator_id) from ai_identities
  where facilitator_id is not null and is_active;

-- contact-queue floor: oldest unaddressed message
select min(created_at) from contact where is_addressed is not true;

Read the full file on GitHub · 80 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.

  1. 6d ago First seen · 80 lines · 0 tokens per session scan A 7fea232e126c

Subscribe to this mod's changes

goals-check is a command published in the GitHub repository mereditharmcgee/the-commons (3 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,029 tokens. 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.