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/mercurialsolo/claudectl/auto-insightsgit clone --depth 1 https://github.com/mercurialsolo/claudectlWrote 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/mercurialsolo/claudectl/auto-insights)<a href="https://agentmods.dev/commands/mercurialsolo/claudectl/auto-insights"><img src="https://agentmods.dev/badge/commands/mercurialsolo/claudectl/auto-insights.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 5.1 | $0.00026 | $0.00316 |
| Opus 5 | $0.00013 | $0.00158 |
| Sonnet 5 | $0.00005 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
auto-insights 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 6d 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
Manage claudectl's auto-insights system, which analyzes brain decision history to detect friction patterns and suggest workflow improvements.
What to do
If the user provides an argument (on, off, or status):
- Run
claudectl --brain --insights {{arg}}to set the insights mode.
If no argument is provided:
- Run
claudectl --brain --insightsto show current insights.
How to present results
Insights are grouped by category:
- Friction Patterns — tools/commands the user frequently rejects (suggest deny rules)
- Error Loops — repeated errors from the same tool (investigate root cause)
- Context Blowouts — sessions frequently hitting high context usage (suggest earlier /compact)
- Recommended Rules — high-confidence patterns that should become auto-rules in
.claudectl.toml - Accuracy Gaps — tools where the brain needs more training data
- Temporal Patterns — time-of-day or error-streak behaviors
- Cost Patterns — burn rate trends and expensive session outliers
For Recommended Rules, show the exact TOML syntax the user can copy into .claudectl.toml.
If the user asks to apply a suggested rule, help them edit their .claudectl.toml directly.
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.
- 6d ago First seen · 31 lines · 26 tokens per session scan A 079fbf8b63d5
auto-insights is a command published in the GitHub repository mercurialsolo/claudectl (197 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 316 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
computer
Drive a computer's screen, mouse, and keyboard.
afsr
Review feature spec - improve the spec itself before implementation (shortcut for feature-spec-review).
research-do
Do research - agent writes findings.
research-spec-review
Review research spec - improve the research brief before execution.
afe
Evaluate feature - code review or comparison (shortcut for feature-eval).
afs
Start feature [agents...] - create workspace and begin implementation (shortcut for feature-start).