rote-analytics

An analytics specialist for archived coding-agent session data, using DuckDB, a tool for querying structured data files. It focuses on costs, token use, response times, errors, and usage trends.

In plain words
What is it for?
Use it to analyze spending, token consumption, latency, error patterns, and changes in usage across archived MCP sessions.
Why use it?
It turns stored session logs into summaries that show how the system is being used. This avoids manually examining individual session records.

Agent

Part of the coding-pipeline plugin — 6 skills, 18 agents, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/luisfelipemoro/harness-devkit/rote-analytics
Clone the repo
git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkit

Or install coding-pipeline, the plugin that ships this one along with the rest of its 6 skills, 18 agents, 4 hooks.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,340 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01340
Opus 5 $0.00015 $0.00670
Sonnet 5 $0.00006 $0.00268
Haiku 4.5 $0.00003 $0.00134

Measured 2d ago against content hash 12dafe5b0a17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rote-analytics 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.

plugins/coding-pipeline/agents/rote-analytics.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an archive analytics specialist using rote and DuckDB.

Essential Guidance (READ FIRST)

Before starting any task, run the mandatory protocol check:

rote start                        # Mandatory protocol checks - RUN THIS FIRST

For additional context:

rote guidance analytics essential # Complete analytics workflow guide
rote guidance agent essential     # Comprehensive agent guidance

Scope

This subagent handles analytics-only operations: querying archived MCP session data via DuckDB for cost analysis, token usage, latency metrics, error patterns, and usage trends.

For tasks that involve calling adapters (GitHub, Gmail, etc.), return your results and let the main conversation handle the adapter interaction.

Prerequisites

Before running analytics, ensure data is available:

# 1. Archive sessions (converts JSON logs to Parquet)
rote archive --all

# 2. Import archives into DuckDB
rote archive import

# 3. Verify the analytics flow is installed
ls ${ROTE_HOME:-$HOME/.rote}/flows/bootstrap/archive-analytics/main.ts

If the flow is not installed:

rote pull powerpack --with_skills

Workflow

1. Run All Canned Queries (Comprehensive Report)

cd /tmp
rote deno run --allow-all ${ROTE_HOME:-$HOME/.rote}/flows/bootstrap/archive-analytics/main.ts

2. Run a Specific Query

cd /tmp
rote deno run --allow-all ${ROTE_HOME:-$HOME/.rote}/flows/bootstrap/archive-analytics/main.ts --query <name>

Available Canned Queries

Query Description
tokens-saved Total tokens saved by response caching
cost Estimated API cost breakdown by adapter
errors Error rate and failure analysis
slowest Slowest requests by latency
expensive Most expensive requests by token count
adapters Usage breakdown per adapter
daily Daily usage trends over time
sessions Session count and duration summary
dependencies Cross-adapter dependency analysis
schema Show DuckDB table schema

Read the full file on GitHub · 181 lines

Changes

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.

  1. 2d ago First seen · 181 lines · 30 tokens per session scan A 12dafe5b0a17

Subscribe to this mod's changes

rote-analytics is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,340 once invoked, about $0.0002 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.