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/DevZonayed/MochiWrote 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/devzonayed/mochi/insights)<a href="https://agentmods.dev/commands/devzonayed/mochi/insights"><img src="https://agentmods.dev/badge/commands/devzonayed/mochi/insights/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/devzonayed/mochi/insights"><img src="https://agentmods.dev/badge/commands/devzonayed/mochi/insights.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 | $0.00015 | $0.00233 |
| Opus 5.5 | $0.00006 | $0.00093 |
| Sonnet 5.5 | $0.00003 | $0.00047 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
insights scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS -H "authorization: Bearer $MOCHI_DASHBOARD_TOKEN" \ What it actually says
For the plugin owner only. Fetches aggregated, content-free usage insights from the self-hosted ingest server and prints them. Regular users do not have credentials and should use /mochi:telemetry show for their own local view.
- Confirm the owner has the dashboard bearer token (or basic-auth) — never hard-code it.
- Fetch and pretty-print the summary:
curl -fsS -H "authorization: Bearer $MOCHI_DASHBOARD_TOKEN" \
https://mochi-insight.nexalance.cloud/v1/summary | python3 -m json.tool
Render the result as: top tools, top MCPs, per-tool error rates, tool co-occurrence, calls-per-task, tools-per-task-category, and the ranked improvement backlog. If the request 401s, the token is missing/wrong; if it times out, check the server health at /v1/health.
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 · 18 lines · 15 tokens per session scan A 96db7511c6ac
insights is a command published in the GitHub repository DevZonayed/Mochi (3 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 233 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
intercept
HTTP sniffer for tandem's Chrome via CDP: captures request+response bodies (including HttpOnly, CSRF tokens, private APIs). Subcommands: start, show, clear, count.
Captures the current page in tandem's Chrome as a PDF (if headless Chrome) or full-page PNG screenshot (in normal tandem mode). Saves to /.claude/tandem/output/.
cookies
Exports cookies from tandem's Chrome via CDP (includes HttpOnly/Secure). Filter with --domain . Formats: list (table, default), json, curl, headers, netscape.
browser-start
../../../commands/browser-start.md.
autoresearch
Autonomous research loop — iteratively edit, test, measure, keep/discard. Usage: /autoresearch [--budget 5m] [--provider ark].
gitlab-scrum
GitLab Scrum management - create/manage issues, labels, milestones, and boards. Use when user says: create issue, list issues, move issue, add label, scrum, kanban, backlog, or task tracking.