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/ttttonyhe/autogrind/startgit 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.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 | $0.00009 | $0.00092 |
| Opus 5 | $0.00005 | $0.00046 |
| Sonnet 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 4d 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.
- 4d 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 4mo ago), licensed MIT. It adds 9 tokens to every session and 92 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
crossframe-essay
使用 CrossFrame Essay 把用户给出的主题、素材或问题写成中文批判性洞察文章。.
crossframe-history
Use CrossFrame History for historical materials, civilization continuity, source-ledger boundaries, dynasty or institutional history, archive-access backlog, FOIA closeout, or local C5 boundary summaries.
crossframe-inquiry
Use CrossFrame Inquiry after a completed CrossFrame diagnosis, article, review, or suite workflow when the user wants follow-up questions, counterexamples, missing evidence, transfer conditions, or action boundaries.
setup
Configure Azure MCP server with Azure CLI authentication.
crossframe-notebook
Use CrossFrame Notebook for bidirectional reading notes on books, essays, theories, excerpts, or citations.
update-scaffold
Check for and apply myPKA scaffold framework updates safely. Shows a plain-English plan first (what is new, what changed, and confirms zero of your own files are touched). Dry-run by default; applies only on explicit confirmation. Never touches your PKM, journal, Expansions, secrets, or databases.