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/benmarte/autoimproveWrote 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/benmarte/autoimprove/status)<a href="https://agentmods.dev/commands/benmarte/autoimprove/status"><img src="https://agentmods.dev/badge/commands/benmarte/autoimprove/status/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/benmarte/autoimprove/status"><img src="https://agentmods.dev/badge/commands/benmarte/autoimprove/status.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 | $0.00011 | $0.00253 |
| Opus 5.5 | $0.00004 | $0.00101 |
| Sonnet 5.5 | $0.00002 | $0.00051 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade A, and why
status 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
Read .claude/autoimprove/log.md from the project root.
If the file doesn't exist, say: "No autoimprove runs yet. Use /autoimprove:improve to start."
Otherwise:
Check for interrupted session
Find the last ## Session — header. If found, check its **Status:** line:
-
If
IN_PROGRESS(interrupted session), show:━━━ Last Session: INTERRUPTED ━━━━━━━━━━━━ 📊 Score: [baseline] → [last score] (+delta) 🔁 Completed: N/M iterations (remaining left) 🎯 Focus: "focus string" 💡 Use /autoimprove:continue to resume ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ -
If
COMPLETEDor no session header (legacy format), show the standard summary.
Standard summary
Summarise:
- Total iterations run
- Wins (kept) vs discards
- Score at start vs current
- Top 3 most impactful changes kept
- Last 3 discarded hypotheses (so we don't repeat them)
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 · 35 lines · 11 tokens per session scan A 12dc2504227c
status is a command published in the GitHub repository benmarte/autoimprove (5 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 253 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
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
feat
Quick feature commit. Use for new feature, add feature, implement, create new.
nyann:diff-profile
Compare two nyann profiles side-by-side and show what changes between them: hooks, branching, CI, documentation, extras, governance. Useful before switching profiles to understand the impact.
summary
Generate a consolidated project brief from design artifacts. For the full spec package with YAML specs and validation, use /compile instead.
tasks
Inspect Modellix task status and recover tasks after a timeout or unknown submission.