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/benmarte/autoimprove/upgradegit clone --depth 1 https://github.com/benmarte/autoimproveWhat 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 | $0.00011 | $0.00258 |
| Opus 5 | $0.00005 | $0.00129 |
| Sonnet 5 | $0.00002 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
upgrade 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 2d 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.
This is a copy
88% identical to upgrade — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Upgrade autoimprove to the latest version. Follow these steps:
Step 1: Check current version
Read the VERSION file in the autoimprove plugin root to get the current version. The plugin root is the directory where this command file lives (go up one level from commands/).
Step 2: Check latest version
Run this command to get the latest release version from GitHub:
gh api repos/benmarte/autoimprove/releases/latest --jq '.tag_name'
Step 3: Compare and upgrade
If the versions match, report: "autoimprove is up to date (v{version})."
If a newer version is available, run the upgrade:
/plugin install autoimprove@autoimprove
Then report:
- "autoimprove upgraded from v{old} to v{new}."
- "Restart Claude Code to use the new version."
Step 4: Show changelog
After upgrading, fetch and display the release notes for the new version:
gh api repos/benmarte/autoimprove/releases/latest --jq '.body'
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.
- 2d ago First seen · 40 lines · 11 tokens per session scan A cc4cec6a944d
upgrade is a command published in the GitHub repository benmarte/autoimprove (5 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 258 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to upgrade, differing in 16 lines, and is treated as a copy.
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-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.
crossframe-teach
Use CrossFrame Teach to explain CrossFrame concepts in plain Chinese.
crossframe-casebook
Use CrossFrame Casebook to turn materials into reusable casebook entries.
newton
Invoke Newton — reasoning and sparring partner mode. Appends "Newton:" to your next prompt so the skill is explicitly triggered.
init
Add codemunch instructions to your project CLAUDE.md for automatic token-efficient exploration.