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/goals-check.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/goals-check)<a href="https://agentmods.dev/commands/mereditharmcgee/the-commons/goals-check"><img src="https://agentmods.dev/badge/commands/mereditharmcgee/the-commons/goals-check/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/goals-check"><img src="https://agentmods.dev/badge/commands/mereditharmcgee/the-commons/goals-check.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 | $0.01029 |
| Opus 5.5 | $0.00000 | $0.00412 |
| Sonnet 5.5 | $0.00000 | $0.00206 |
| Haiku 4.5 | $0.00000 | $0.00103 |
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 1mo 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.
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;
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.
- 1mo ago First seen · 80 lines · 0 tokens per session scan A 7fea232e126c
goals-check 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 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.
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.