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.
git clone --depth 1 https://github.com/ttttonyhe/autogrindWrote 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/ttttonyhe/autogrind/start)<a href="https://agentmods.dev/commands/ttttonyhe/autogrind/start"><img src="https://agentmods.dev/badge/commands/ttttonyhe/autogrind/start/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/ttttonyhe/autogrind/start"><img src="https://agentmods.dev/badge/commands/ttttonyhe/autogrind/start.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 | $0.00009 | $0.00092 |
| Opus 5.5 | $0.00004 | $0.00037 |
| Sonnet 5.5 | $0.00002 | $0.00018 |
| Haiku 4.5 | $0.00001 | $0.00009 |
Grade A, and why
start 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.
What it actually says
Use the Skill tool to load and follow the autogrind:autogrind skill.
$ARGUMENTS is the session focus that biases the first cycle's Overview and Plan toward that area. It is NOT a terminal goal — completing it is not a stop condition. The Iron Law applies from the first cycle: keep grinding until the user sends an explicit stop signal.
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 · 8 lines · 9 tokens per session scan A 2acce7c126b4
start is a command published in the GitHub repository ttttonyhe/autogrind (7 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 92 once invoked, about $0.0000 per session on Opus 5.5. 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
init
Initialize configurations for Supabase local development.
secrets
Provides tools for managing environment variables and secrets for your Supabase project.
stop
Stops the Supabase local development stack.
tidy
Consistency check for non-code repos with INDEX.md hierarchy. Verifies INDEX.md accuracy, MEMORY.md references, orphaned files, stale dates, and WAITING markers.
start-0-5.en
Auto-run by AI: Run uv run python tools/setupprogress.py show to display the current setup progress.
setup-m365cli.es
Lesson command — Setup de M365 CLI.